1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
1465
1466
1467
1468
1469
1470
1471
1472
1473
1474
1475
1476
1477
1478
1479
1480
1481
1482
1483
1484
1485
1486
1487
1488
1489
1490
1491
1492
1493
1494
1495
1496
1497
1498
1499
1500
1501
1502
1503
1504
1505
1506
1507
1508
1509
1510
1511
1512
1513
1514
1515
1516
1517
1518
1519
1520
1521
1522
1523
1524
1525
1526
1527
1528
1529
1530
1531
1532
1533
1534
1535
1536
1537
1538
1539
1540
1541
1542
1543
1544
1545
1546
1547
1548
1549
1550
1551
1552
1553
1554
1555
1556
1557
1558
1559
1560
1561
1562
1563
1564
1565
1566
1567
1568
1569
1570
1571
1572
1573
1574
1575
1576
1577
1578
1579
1580
1581
1582
1583
1584
1585
1586
1587
1588
1589
1590
1591
1592
1593
1594
1595
1596
1597
1598
1599
1600
1601
1602
1603
1604
1605
1606
1607
1608
1609
1610
1611
1612
1613
1614
1615
1616
1617
1618
1619
1620
1621
1622
1623
1624
1625
1626
1627
1628
1629
1630
1631
1632
1633
1634
1635
1636
1637
1638
1639
1640
1641
1642
1643
1644
1645
1646
1647
1648
1649
1650
1651
1652
1653
1654
1655
1656
1657
1658
1659
1660
1661
1662
1663
1664
1665
1666
1667
1668
1669
1670
1671
1672
1673
1674
1675
1676
1677
1678
1679
1680
1681
1682
1683
1684
1685
1686
1687
1688
1689
1690
1691
1692
1693
1694
1695
1696
1697
1698
1699
1700
1701
1702
1703
1704
1705
1706
1707
1708
1709
1710
1711
1712
1713
1714
1715
1716
1717
1718
1719
1720
1721
1722
1723
1724
1725
1726
1727
1728
1729
1730
1731
1732
1733
1734
1735
1736
1737
1738
1739
1740
1741
1742
1743
1744
1745
1746
1747
1748
1749
1750
1751
1752
1753
1754
1755
1756
1757
1758
1759
1760
1761
1762
1763
1764
1765
1766
1767
1768
1769
1770
1771
1772
1773
1774
1775
1776
1777
1778
1779
1780
1781
1782
1783
1784
1785
1786
1787
1788
1789
1790
1791
1792
1793
1794
1795
1796
1797
1798
1799
1800
1801
1802
1803
1804
1805
1806
1807
1808
1809
1810
1811
1812
1813
1814
1815
1816
1817
1818
1819
1820
1821
1822
1823
1824
1825
1826
1827
1828
1829
1830
1831
1832
1833
1834
1835
1836
1837
1838
1839
1840
1841
1842
1843
1844
1845
1846
1847
1848
1849
1850
1851
1852
1853
1854
1855
1856
1857
1858
1859
1860
1861
1862
1863
1864
1865
1866
1867
1868
1869
1870
1871
1872
1873
1874
1875
1876
1877
1878
1879
1880
1881
1882
1883
1884
1885
1886
1887
1888
1889
1890
1891
1892
1893
1894
1895
1896
1897
1898
1899
1900
1901
1902
1903
1904
1905
1906
1907
1908
1909
1910
1911
1912
1913
1914
1915
1916
1917
1918
1919
1920
1921
1922
1923
1924
1925
1926
1927
1928
1929
1930
1931
1932
1933
1934
1935
1936
1937
1938
1939
1940
1941
1942
1943
1944
1945
1946
1947
1948
1949
1950
1951
1952
1953
1954
1955
1956
1957
1958
1959
1960
1961
1962
1963
1964
1965
1966
1967
1968
1969
1970
1971
1972
1973
1974
1975
1976
1977
1978
1979
1980
1981
1982
1983
1984
1985
1986
1987
1988
1989
1990
1991
1992
1993
1994
1995
1996
1997
1998
1999
2000
2001
2002
2003
2004
2005
2006
2007
2008
2009
2010
2011
2012
2013
2014
2015
2016
2017
2018
2019
2020
2021
2022
2023
2024
2025
2026
2027
2028
2029
2030
2031
2032
2033
2034
2035
2036
2037
2038
2039
2040
2041
2042
2043
2044
2045
2046
2047
2048
2049
2050
2051
2052
2053
2054
2055
2056
2057
2058
2059
2060
2061
2062
2063
2064
2065
2066
2067
2068
2069
2070
2071
2072
2073
2074
2075
2076
2077
2078
2079
2080
2081
2082
2083
2084
2085
2086
2087
2088
2089
2090
2091
2092
2093
2094
2095
2096
2097
2098
2099
2100
2101
2102
2103
2104
2105
2106
2107
2108
2109
2110
2111
2112
2113
2114
2115
2116
2117
2118
2119
2120
2121
2122
2123
2124
2125
2126
2127
2128
2129
2130
2131
2132
2133
2134
2135
2136
2137
2138
2139
2140
2141
2142
2143
2144
2145
2146
2147
2148
2149
2150
2151
2152
2153
2154
2155
2156
2157
2158
2159
2160
2161
2162
2163
2164
2165
2166
2167
2168
2169
2170
2171
2172
2173
2174
2175
2176
2177
2178
2179
2180
2181
2182
2183
2184
2185
2186
2187
2188
2189
2190
2191
2192
2193
2194
2195
2196
2197
2198
2199
2200
2201
2202
2203
2204
2205
2206
2207
2208
2209
2210
2211
2212
2213
2214
2215
2216
2217
2218
2219
2220
2221
2222
2223
2224
2225
2226
2227
2228
2229
2230
2231
2232
2233
2234
2235
2236
2237
2238
2239
2240
2241
2242
2243
2244
2245
2246
2247
2248
2249
2250
2251
2252
2253
2254
2255
2256
2257
2258
2259
2260
2261
2262
2263
2264
2265
2266
2267
2268
2269
2270
2271
2272
2273
2274
2275
2276
2277
2278
2279
2280
2281
2282
2283
2284
2285
2286
2287
2288
2289
2290
2291
2292
2293
2294
2295
2296
2297
2298
2299
2300
2301
2302
2303
2304
2305
2306
2307
2308
2309
2310
2311
2312
2313
2314
2315
2316
2317
2318
2319
2320
2321
2322
2323
2324
2325
2326
2327
2328
2329
2330
2331
2332
2333
2334
2335
2336
2337
2338
2339
2340
2341
2342
2343
2344
2345
2346
2347
2348
2349
2350
2351
2352
2353
2354
2355
2356
2357
2358
2359
2360
2361
2362
2363
2364
2365
2366
2367
2368
2369
2370
2371
2372
2373
2374
2375
2376
2377
2378
2379
2380
2381
2382
2383
2384
2385
2386
2387
2388
2389
2390
2391
2392
2393
2394
2395
2396
2397
2398
2399
2400
2401
2402
2403
2404
2405
2406
2407
2408
2409
2410
2411
2412
2413
2414
2415
2416
2417
2418
2419
2420
2421
2422
2423
2424
2425
2426
2427
2428
2429
2430
2431
2432
2433
2434
2435
2436
2437
2438
2439
2440
2441
2442
2443
2444
2445
2446
2447
2448
2449
2450
2451
2452
2453
2454
2455
2456
2457
2458
2459
2460
2461
2462
2463
2464
2465
2466
2467
2468
2469
2470
2471
2472
2473
2474
2475
2476
2477
2478
2479
2480
2481
2482
2483
2484
2485
2486
2487
2488
2489
2490
2491
2492
2493
2494
2495
2496
2497
2498
2499
2500
2501
2502
2503
2504
2505
2506
2507
2508
2509
2510
2511
2512
2513
2514
2515
2516
2517
2518
2519
2520
2521
2522
2523
2524
2525
2526
2527
2528
2529
2530
2531
2532
2533
2534
2535
2536
2537
2538
2539
2540
2541
2542
2543
2544
2545
2546
2547
2548
2549
2550
2551
2552
2553
2554
2555
2556
2557
2558
2559
2560
2561
2562
2563
2564
2565
2566
2567
2568
2569
2570
2571
2572
2573
2574
2575
2576
2577
2578
2579
2580
2581
2582
2583
2584
2585
2586
2587
2588
2589
2590
2591
2592
2593
2594
2595
2596
2597
2598
2599
2600
2601
2602
2603
2604
2605
2606
2607
2608
2609
2610
2611
2612
2613
2614
2615
2616
2617
2618
2619
2620
2621
2622
2623
2624
2625
2626
2627
2628
2629
2630
2631
2632
2633
2634
2635
2636
2637
2638
2639
2640
2641
2642
2643
2644
2645
2646
2647
2648
2649
2650
2651
2652
2653
2654
2655
2656
2657
2658
2659
2660
2661
2662
2663
2664
2665
2666
2667
2668
2669
2670
2671
2672
2673
2674
2675
2676
2677
2678
2679
2680
2681
2682
2683
2684
2685
2686
2687
2688
2689
2690
2691
2692
2693
2694
2695
2696
2697
2698
2699
2700
2701
2702
2703
2704
2705
2706
2707
2708
2709
2710
2711
2712
2713
2714
2715
2716
2717
2718
2719
2720
2721
2722
2723
2724
2725
2726
2727
2728
2729
2730
2731
2732
2733
2734
2735
2736
2737
2738
2739
2740
2741
2742
2743
2744
2745
2746
2747
2748
2749
2750
2751
2752
2753
2754
2755
2756
2757
2758
2759
2760
2761
2762
2763
2764
2765
2766
2767
2768
2769
2770
2771
2772
2773
2774
2775
2776
2777
2778
2779
2780
2781
2782
2783
2784
2785
2786
2787
2788
2789
2790
2791
2792
2793
2794
2795
2796
2797
2798
2799
2800
2801
2802
2803
2804
2805
2806
2807
2808
2809
2810
2811
2812
2813
2814
2815
2816
2817
2818
2819
2820
2821
2822
2823
2824
2825
2826
2827
2828
2829
2830
2831
2832
2833
2834
2835
2836
2837
2838
2839
2840
2841
2842
2843
2844
2845
2846
2847
2848
2849
2850
2851
2852
2853
2854
2855
2856
2857
2858
2859
2860
2861
2862
2863
2864
2865
2866
2867
2868
2869
2870
2871
2872
2873
2874
2875
2876
2877
2878
2879
2880
2881
2882
2883
2884
2885
2886
2887
2888
2889
2890
2891
2892
2893
2894
2895
2896
2897
2898
2899
2900
2901
2902
2903
2904
2905
2906
2907
2908
2909
2910
2911
2912
2913
2914
2915
2916
2917
2918
2919
2920
2921
2922
2923
2924
2925
2926
2927
2928
2929
2930
2931
2932
2933
2934
2935
2936
2937
2938
2939
2940
2941
2942
2943
2944
2945
2946
2947
2948
2949
2950
2951
2952
2953
2954
2955
2956
2957
2958
2959
2960
2961
2962
2963
2964
2965
2966
2967
2968
2969
2970
2971
2972
2973
2974
2975
2976
2977
2978
2979
2980
2981
2982
2983
2984
2985
2986
2987
2988
2989
2990
2991
2992
2993
2994
2995
2996
2997
2998
2999
3000
3001
3002
3003
3004
3005
3006
3007
3008
3009
3010
3011
3012
3013
3014
3015
3016
3017
3018
3019
3020
3021
3022
3023
3024
3025
3026
3027
3028
3029
3030
3031
3032
3033
3034
3035
3036
3037
3038
3039
3040
3041
3042
3043
3044
3045
3046
3047
3048
3049
3050
3051
3052
3053
3054
3055
3056
3057
3058
3059
3060
3061
3062
3063
3064
3065
3066
3067
3068
3069
3070
3071
3072
3073
3074
3075
3076
3077
3078
3079
3080
3081
3082
3083
3084
3085
3086
3087
3088
3089
3090
3091
3092
3093
3094
3095
3096
3097
3098
3099
3100
3101
3102
3103
3104
3105
3106
3107
3108
3109
3110
3111
3112
3113
3114
3115
3116
3117
3118
3119
3120
3121
3122
3123
3124
3125
3126
3127
3128
3129
3130
3131
3132
3133
3134
3135
3136
3137
3138
3139
3140
3141
3142
3143
3144
3145
3146
3147
3148
3149
3150
3151
3152
3153
3154
3155
3156
3157
3158
3159
3160
3161
3162
3163
3164
3165
3166
3167
3168
3169
3170
3171
3172
3173
3174
3175
3176
3177
3178
3179
3180
3181
3182
3183
3184
3185
3186
3187
3188
3189
3190
3191
3192
3193
3194
3195
3196
3197
3198
3199
3200
3201
3202
3203
3204
3205
3206
3207
3208
3209
3210
3211
3212
3213
3214
3215
3216
3217
3218
3219
3220
3221
3222
3223
3224
3225
3226
3227
3228
3229
3230
3231
3232
3233
3234
3235
3236
3237
3238
3239
3240
3241
3242
3243
3244
3245
3246
3247
3248
3249
3250
3251
3252
3253
3254
3255
3256
3257
3258
3259
3260
3261
3262
3263
3264
3265
3266
3267
3268
3269
3270
3271
3272
3273
3274
3275
3276
3277
3278
3279
3280
3281
3282
3283
3284
3285
3286
3287
3288
3289
3290
3291
3292
3293
3294
3295
3296
3297
3298
3299
3300
3301
3302
3303
3304
3305
3306
3307
3308
3309
3310
3311
3312
3313
3314
3315
3316
3317
3318
3319
3320
3321
3322
3323
3324
3325
3326
3327
3328
3329
3330
3331
3332
3333
3334
3335
3336
3337
3338
3339
3340
3341
3342
3343
3344
3345
3346
3347
3348
3349
3350
3351
3352
3353
3354
3355
3356
3357
3358
3359
3360
3361
3362
3363
3364
3365
3366
3367
3368
3369
3370
3371
3372
3373
3374
3375
3376
3377
3378
3379
3380
3381
3382
3383
3384
3385
3386
3387
3388
3389
3390
3391
3392
3393
3394
3395
3396
3397
3398
3399
3400
3401
3402
3403
3404
3405
3406
3407
3408
3409
3410
3411
3412
3413
3414
3415
3416
3417
3418
3419
3420
3421
3422
3423
3424
3425
3426
3427
3428
3429
3430
3431
3432
3433
3434
3435
3436
3437
3438
3439
3440
3441
3442
3443
3444
3445
3446
3447
3448
3449
3450
3451
3452
3453
3454
3455
3456
3457
3458
3459
3460
3461
3462
3463
3464
3465
3466
3467
3468
3469
3470
3471
3472
3473
3474
3475
3476
3477
3478
3479
3480
3481
3482
3483
3484
3485
3486
3487
3488
3489
3490
3491
3492
3493
3494
3495
3496
3497
3498
3499
3500
3501
3502
3503
3504
3505
3506
3507
3508
3509
3510
3511
3512
3513
3514
3515
3516
3517
3518
3519
3520
3521
3522
3523
3524
3525
3526
3527
3528
3529
3530
3531
3532
3533
3534
3535
3536
3537
3538
3539
3540
3541
3542
3543
3544
3545
3546
3547
3548
3549
3550
3551
3552
3553
3554
3555
3556
3557
3558
3559
3560
3561
3562
3563
3564
3565
3566
3567
3568
3569
3570
3571
3572
3573
3574
3575
3576
3577
3578
3579
3580
3581
3582
3583
3584
3585
3586
3587
3588
3589
3590
3591
3592
3593
3594
3595
3596
3597
3598
3599
3600
3601
3602
3603
3604
3605
3606
3607
3608
3609
3610
3611
3612
3613
3614
3615
3616
3617
3618
3619
3620
3621
3622
3623
3624
3625
3626
3627
3628
3629
3630
3631
3632
3633
3634
3635
3636
3637
3638
3639
3640
3641
3642
3643
3644
3645
3646
3647
3648
3649
3650
3651
3652
3653
3654
3655
3656
3657
3658
3659
3660
3661
3662
3663
3664
3665
3666
3667
3668
3669
3670
3671
3672
3673
3674
3675
3676
3677
3678
3679
3680
3681
3682
3683
3684
3685
3686
3687
3688
3689
3690
3691
3692
3693
3694
3695
3696
3697
3698
3699
3700
3701
3702
3703
3704
3705
3706
3707
3708
3709
3710
3711
3712
3713
3714
3715
3716
3717
3718
3719
3720
3721
3722
3723
3724
3725
3726
3727
3728
3729
3730
3731
3732
3733
3734
3735
3736
3737
3738
3739
3740
3741
3742
3743
3744
3745
3746
3747
3748
3749
3750
3751
3752
3753
3754
3755
3756
3757
3758
3759
3760
3761
3762
3763
3764
3765
3766
3767
3768
3769
3770
3771
3772
3773
3774
3775
3776
3777
3778
3779
3780
3781
3782
3783
3784
3785
3786
3787
3788
3789
3790
3791
3792
3793
3794
3795
3796
3797
3798
3799
3800
3801
3802
3803
3804
3805
3806
3807
3808
3809
3810
3811
3812
3813
3814
3815
3816
3817
3818
3819
3820
3821
3822
3823
3824
3825
3826
3827
3828
3829
3830
3831
3832
3833
3834
3835
3836
3837
3838
3839
3840
3841
3842
3843
3844
3845
3846
3847
3848
3849
3850
3851
3852
3853
3854
3855
3856
3857
3858
3859
3860
3861
3862
3863
3864
3865
3866
3867
3868
3869
3870
3871
3872
3873
3874
3875
3876
3877
3878
3879
3880
3881
3882
3883
3884
3885
3886
3887
3888
3889
3890
3891
3892
3893
3894
3895
3896
3897
3898
3899
3900
3901
3902
3903
3904
3905
3906
3907
3908
3909
3910
3911
3912
3913
3914
3915
3916
3917
3918
3919
3920
3921
3922
3923
3924
3925
3926
3927
3928
3929
3930
3931
3932
3933
3934
3935
3936
3937
3938
3939
3940
3941
3942
3943
3944
3945
3946
3947
3948
3949
3950
3951
3952
3953
3954
3955
3956
3957
3958
3959
3960
3961
3962
3963
3964
3965
3966
3967
3968
3969
3970
3971
3972
3973
3974
3975
3976
3977
3978
3979
3980
3981
3982
3983
3984
3985
3986
3987
3988
3989
3990
3991
3992
3993
3994
3995
3996
3997
3998
3999
4000
4001
4002
4003
4004
4005
4006
4007
4008
4009
4010
4011
4012
4013
4014
4015
4016
4017
4018
4019
4020
4021
4022
4023
4024
4025
4026
4027
4028
4029
4030
4031
4032
4033
4034
4035
4036
4037
4038
4039
4040
4041
4042
4043
4044
4045
4046
4047
4048
4049
4050
4051
4052
4053
4054
4055
4056
4057
4058
4059
4060
4061
4062
4063
4064
4065
4066
4067
4068
4069
4070
4071
4072
4073
4074
4075
4076
4077
4078
4079
4080
4081
4082
4083
4084
4085
4086
4087
4088
4089
4090
4091
4092
4093
4094
4095
4096
4097
4098
4099
4100
4101
|
#!/usr/bin/env perl
##!/usr/bin/perl -w
# latexdiff - differences two latex files on the word level
# and produces a latex file with the differences marked up.
#
# Copyright (C) 2004-12 F J Tilmann (tilmann@gfz-potsdam.de)
#
# Repository/issue tracker: https://github.com/ftilmann/latexdiff
# CTAN page: http://www.ctan.org/tex-archive/support/latexdiff
#
# This program is free software: you can redistribute it and/or modify
# it under the terms of the GNU General Public License as published by
# the Free Software Foundation, either version 3 of the License, or
# (at your option) any later version.
#
# This program is distributed in the hope that it will be useful,
# but WITHOUT ANY WARRANTY; without even the implied warranty of
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
# GNU General Public License for more details.
# You should have received a copy of the GNU General Public License
# along with this program. If not, see <http://www.gnu.org/licenses/>.
#
# Detailed usage information at the end of the file
#
# ToDo:
#
# Version 1.0.4
# - introduce list UNSAFEMATHCMD, which holds list of commands which cannot be marked up with \DIFadd or \DIFdel commands (only relevant for WHOLE and COARSE math markup modes)
# - new subtype LABEL which gives each change a label. This can later be used to only display pages where changes
# have been made (instructions for that are put as comments into the diff'ed file) inspired by answer on http://tex.stackexchange.com/questions/166049/invisible-markers-in-pdfs-using-pdflatex
# - Configuration variables take into accout some commands from additional packages:
# tikzpicture environment now treated as PICTUREENV, and \smallmatrix in ARRENV (amsmath)
# - --flatten: support for \subfile command (subfiles package) (in response to http://tex.stackexchange.com/questions/167620/latexdiff-with-subfiles )
# - --flatten: \bibliography commands expand if corresponding bbl file present
# - angled bracket optional commands now parsed correctly (patch #3570) submitted by Dave Kleinschmidt (thanks)
# - \RequirePackage now treated as synonym of \usepackage with respect to setting packages
# - special rules for apacite package (redefine citation commands)
# - recognise /dev/null as 'file-like' arguments for --preamble and --config options
# - fix units package incompatibility with ulem for text maths statements $ ..$ (thanks to Stuart Prescott for reporting this)
# - amsmath environment cases treated correctly (Bug fix #19029) (thanks to Jalar)
# - {,} in comments no longer confuse latexdiff (Bug fix #19146)
# - \% in one-letter sub/Superscripts was not converted correctly
#
# Version 1.0.3
# - fix bug in add_safe_commands that made latexdiff hang on DeclareMathOperator
# command in preamble
# - \(..\) inline math expressions were not parsed correctly, if they contained a linebreak
# - applied patch contributed by tomflannaghan via Berlios: [ Patch #3431 ] Adds correct handling of \left< and \right>
# - \$ is treated correctly as a literal dollar sign (thanks to Reed Cartwright and Joshua Miller for reporting this bug
# and sketching out the solution)
# - \^ and \_ are correctly interpreted as accent and underlined space, respectively, not as superscript of subscript
# (thanks to Wail Yahyaoui for pointing out this bug)
#
# Version 1.0.1 - treat \big,\bigg etc. equivalently to \left and
# \right - include starred version in MATHENV - apply
# - flatten recursively and --flatten expansion is now
# aware of comments (thanks to Tim Connors for patch)
# - Change to post-processing for more reliability for
# deleted math environments
# - On linux systems, recognise and remove DOS style newlines
# - Provide markup for some special preamble commands (\title,
# \author,\date,
# - configurable by setting context2cmd
# - for styles using ulem package, remove \emph and \text.. from list of
# safe commands in order to allow linebreaks within the
# highlighted sections.
# - for ulem style, now show citations by enclosing them in \mbox commands.
# This unfortunately implies linebreaks within citations no longer function,
# so this functionality can be turned off (Option --disable-citation-markup).
# With --enable-citation-markup, the mbox markup is forced for other styles)
# - new substyle COLOR. This is particularly useful for marking up citations
# and some special post-processing is implemented to retain cite
# commands in deleted blocks.
# - four different levels of math-markup
# - Option --driver for choosing driver for modes employing changebar package
# - accept \\* as valid command (and other commands of form \.*). Also accept
# \<nl> (backslashed newline)
# - some typo fixes, include commands defined in preamble as safe commands
# (Sebastian Gouezel)
# - include compared filenames as comments as line 2 and 3 of
# the preamble (can be modified with option --label, and suppressed with
# --no-label), option --visible-label to show files in generated pdf or dvi
# at the beginning of main document
#
# Version 0.5 A number of minor improvements based on feedback
# Deleted blocks are now shown before added blocks
# Package specific processing
#
# Version 0.43 unreleased typo in list of styles at the end
# Add protect to all \cbstart, \cbend commands
# More robust substitution of deleted math commands
#
# Version 0.42 November 06 Bug fixes only
#
# Version 0.4 March 06 option for fast differencing using UNIX diff command, several minor bug fixes (\par bug, improved highlighting of textcmds)
#
# Version 0.3 August 05 improved parsing of displayed math, --allow-spaces
# option, several minor bug fixes
#
# Version 0.25 October 04 Fix bug with deleted equations, add math mode commands to safecmd, add | to allowed interpunctuation signs
# Version 0.2 September 04 extension to utf-8 and variable encodings
# Version 0.1 August 04 First public release
# Inserted block for differenceing
# use Algorithm::Diff qw(traverse_sequences);
# in standard version
# The following BEGIN block contains a verbatim copy of
# Ned Konz' Algorithm::Diff package version 1.15 except
# that subroutine _longestCommonSubsequence has been replace by
# a routine which internally uses the UNIX diff command for
# the differencing rather than the Perl routines if the
# length of the sequences exceeds some threshold.
# Also, all POD documentation has been stripped out.
#
# (the distribution on which this modification is based is available
# from http://search.cpan.org/~nedkonz/Algorithm-Diff-1.15
# the most recent version can be found via http://search.cpan.org/search?module=Algorithm::Diff )
# Please note that the LICENCSE for Algorithm::Diff :
# "Copyright (c) 2000-2002 Ned Konz. All rights reserved.
# This program is free software;
# you can redistribute it and/or modify it under the same terms
# as Perl itself."
# The fast-differencing version of latexdiff is provided as a convenience
# for latex users under Unix-like systems which have a 'diff' command.
# If you believe
# the inlining of Algorithm::Diff violates its license please contact
# me and I will modify the latexdiff distribution accordingly.
# Frederik Tilmann (tilmann@esc.cam.ac.uk)
# Jonathan Paisley is acknowledged for the idea of using the system diff
# command to achieve shorter running times
BEGIN {
package Algorithm::Diff;
use strict;
use vars qw($VERSION @EXPORT_OK @ISA @EXPORT);
use integer; # see below in _replaceNextLargerWith() for mod to make
# if you don't use this
require Exporter;
@ISA = qw(Exporter);
@EXPORT = qw();
@EXPORT_OK = qw(LCS diff traverse_sequences traverse_balanced sdiff);
$VERSION = sprintf('%d.%02d fast', (q$Revision: 1.15 $ =~ /\d+/g));
# Global parameters
use File::Temp qw/tempfile/;
# if larger number of elements in longestCommonSubsequence smaller than
# this number, then use internal algorithm, otherwise use UNIX diff
use constant THRESHOLD => 100 ;
# Detect whether diff --minimal option is available
# if yes we use it
use constant MINIMAL => ( system('diff','--minimal','/dev/null','/dev/null') >> 8 ==0 ? "--minimal" : "" ) ;
# McIlroy-Hunt diff algorithm
# Adapted from the Smalltalk code of Mario I. Wolczko, <mario@wolczko.com>
# by Ned Konz, perl@bike-nomad.com
# Create a hash that maps each element of $aCollection to the set of positions
# it occupies in $aCollection, restricted to the elements within the range of
# indexes specified by $start and $end.
# The fourth parameter is a subroutine reference that will be called to
# generate a string to use as a key.
# Additional parameters, if any, will be passed to this subroutine.
#
# my $hashRef = _withPositionsOfInInterval( \@array, $start, $end, $keyGen );
sub _withPositionsOfInInterval
{
my $aCollection = shift; # array ref
my $start = shift;
my $end = shift;
my $keyGen = shift;
my %d;
my $index;
for ( $index = $start ; $index <= $end ; $index++ )
{
my $element = $aCollection->[$index];
my $key = &$keyGen( $element, @_ );
if ( exists( $d{$key} ) )
{
unshift ( @{ $d{$key} }, $index );
}
else
{
$d{$key} = [$index];
}
}
return wantarray ? %d : \%d;
}
# Find the place at which aValue would normally be inserted into the array. If
# that place is already occupied by aValue, do nothing, and return undef. If
# the place does not exist (i.e., it is off the end of the array), add it to
# the end, otherwise replace the element at that point with aValue.
# It is assumed that the array's values are numeric.
# This is where the bulk (75%) of the time is spent in this module, so try to
# make it fast!
sub _replaceNextLargerWith
{
my ( $array, $aValue, $high ) = @_;
$high ||= $#$array;
# off the end?
if ( $high == -1 || $aValue > $array->[-1] )
{
push ( @$array, $aValue );
return $high + 1;
}
# binary search for insertion point...
my $low = 0;
my $index;
my $found;
while ( $low <= $high )
{
$index = ( $high + $low ) / 2;
# $index = int(( $high + $low ) / 2); # without 'use integer'
$found = $array->[$index];
if ( $aValue == $found )
{
return undef;
}
elsif ( $aValue > $found )
{
$low = $index + 1;
}
else
{
$high = $index - 1;
}
}
# now insertion point is in $low.
$array->[$low] = $aValue; # overwrite next larger
return $low;
}
# This method computes the longest common subsequence in $a and $b.
# Result is array or ref, whose contents is such that
# $a->[ $i ] == $b->[ $result[ $i ] ]
# foreach $i in ( 0 .. $#result ) if $result[ $i ] is defined.
# An additional argument may be passed; this is a hash or key generating
# function that should return a string that uniquely identifies the given
# element. It should be the case that if the key is the same, the elements
# will compare the same. If this parameter is undef or missing, the key
# will be the element as a string.
# By default, comparisons will use "eq" and elements will be turned into keys
# using the default stringizing operator '""'.
# Additional parameters, if any, will be passed to the key generation routine.
sub _longestCommonSubsequence
{
my $a = shift; # array ref
my $b = shift; # array ref
my $keyGen = shift; # code ref
my $compare; # code ref
# set up code refs
# Note that these are optimized.
if ( !defined($keyGen) ) # optimize for strings
{
$keyGen = sub { $_[0] };
$compare = sub { my ( $a, $b ) = @_; $a eq $b };
}
else
{
$compare = sub {
my $a = shift;
my $b = shift;
&$keyGen( $a, @_ ) eq &$keyGen( $b, @_ );
};
}
my ( $aStart, $aFinish, $bStart, $bFinish, $matchVector ) =
( 0, $#$a, 0, $#$b, [] );
# Check whether to use internal routine (small number of elements)
# or use it as a wrapper for UNIX diff
if ( ( $#$a > $#$b ? $#$a : $#$b) < THRESHOLD ) {
### print STDERR "DEBUG: regular longestCommonSubsequence\n";
# First we prune off any common elements at the beginning
while ( $aStart <= $aFinish
and $bStart <= $bFinish
and &$compare( $a->[$aStart], $b->[$bStart], @_ ) )
{
$matchVector->[ $aStart++ ] = $bStart++;
}
# now the end
while ( $aStart <= $aFinish
and $bStart <= $bFinish
and &$compare( $a->[$aFinish], $b->[$bFinish], @_ ) )
{
$matchVector->[ $aFinish-- ] = $bFinish--;
}
# Now compute the equivalence classes of positions of elements
my $bMatches =
_withPositionsOfInInterval( $b, $bStart, $bFinish, $keyGen, @_ );
my $thresh = [];
my $links = [];
my ( $i, $ai, $j, $k );
for ( $i = $aStart ; $i <= $aFinish ; $i++ )
{
$ai = &$keyGen( $a->[$i], @_ );
if ( exists( $bMatches->{$ai} ) )
{
$k = 0;
for $j ( @{ $bMatches->{$ai} } )
{
# optimization: most of the time this will be true
if ( $k and $thresh->[$k] > $j and $thresh->[ $k - 1 ] < $j )
{
$thresh->[$k] = $j;
}
else
{
$k = _replaceNextLargerWith( $thresh, $j, $k );
}
# oddly, it's faster to always test this (CPU cache?).
if ( defined($k) )
{
$links->[$k] =
[ ( $k ? $links->[ $k - 1 ] : undef ), $i, $j ];
}
}
}
}
if (@$thresh)
{
for ( my $link = $links->[$#$thresh] ; $link ; $link = $link->[0] )
{
$matchVector->[ $link->[1] ] = $link->[2];
}
}
}
else {
my ($fha,$fhb,$fna,$fnb,$ele,$key);
my ($alines,$blines,$alb,$alf,$blb,$blf);
my ($minimal)=MINIMAL;
# large number of elements, use system diff
### print STDERR "DEBUG: fast (diff) longestCommonSubsequence\n";
($fha,$fna)=tempfile("DiffA-XXXX") or die "_longestCommonSubsequence: Cannot open tempfile for sequence A";
($fhb,$fnb)=tempfile("DiffB-XXXX") or die "_longestCommonSubsequence: Cannot open tempfile for sequence B";
# prepare sequence A
foreach $ele ( @$a ) {
$key=&$keyGen( $ele, @_ );
$key =~ s/\\/\\\\/g ;
$key =~ s/\n/\\n/sg ;
print $fha "$key\n" ;
}
close($fha);
# prepare sequence B
foreach $ele ( @$b ) {
$key=&$keyGen( $ele, @_ );
$key =~ s/\\/\\\\/g ;
$key =~ s/\n/\\n/sg ;
print $fhb "$key\n" ;
}
close($fhb);
open(DIFFPIPE, "diff $minimal $fna $fnb |") or die "_longestCommonSubsequence: Cannot launch diff process. $!" ;
# The diff line numbering begins with 1, but Perl subscripts start with 0
# We follow the diff numbering but substract 1 when assigning to matchVector
$aStart++; $bStart++ ; $aFinish++ ; $bFinish++ ;
while( <DIFFPIPE> ) {
if ( ($alines,$blines) = ( m/^(\d*(?:,\d*)?)?c(\d*(?:,\d*)?)?$/ ) ) {
($alb,$alf)=split(/,/,$alines);
($blb,$blf)=split(/,/,$blines);
$alf=$alb unless defined($alf);
$blf=$blb unless defined($blf);
while($aStart < $alb ) {
$matchVector->[ -1 + $aStart++ ] = -1 + $bStart++ ;
}
# check for consistency
$bStart==$blb or die "_longestCommonSubsequence: Fatal error in interpreting diff output: Inconsistency in changed sequence";
$aStart=$alf+1;
$bStart=$blf+1;
}
elsif ( ($alb,$blines) = ( m/^(\d*)a(\d*(?:,\d*)?)$/ ) ) {
($blb,$blf)=split(/,/,$blines);
$blf=$blb unless defined($blf);
while ( $bStart < $blb ) {
$matchVector->[ -1 + $aStart++ ] = -1 + $bStart++ ;
}
$aStart==$alb+1 or die "_longestCommonSubsequence: Fatal error in interpreting diff output: Inconsistency in appended sequence near elements $aStart and $bStart";
$bStart=$blf+1;
}
elsif ( ($alines,$blb) = ( m/^(\d*(?:,\d*)?)d(\d*)$/ ) ) {
($alb,$alf)=split(/,/,$alines);
$alf=$alb unless defined($alf);
while ( $aStart < $alb ) {
$matchVector->[ -1 + $aStart++ ] = -1 + $bStart++ ;
}
$bStart==$blb+1 or die "_longestCommonSubsequence: Fatal error in interpreting diff output: Inconsistency in deleted sequence near elements $aStart and $bStart";
$aStart=$alf+1;
}
elsif ( m/^Binary files/ ) {
# if diff reports it is a binary file force --text mode. I do not like
# to always use this option because it is probably only available in GNU diff
open(DIFFPIPE, "diff --text $fna $fnb |") or die "Cannot launch diff process. $!" ;
}
# Default: just skip line
}
while ($aStart <= $aFinish ) {
$matchVector->[ -1 + $aStart++ ] = -1 + $bStart++ ;
}
$bStart==$bFinish+1 or die "_longestCommonSubsequence: Fatal error in interpreting diff output: Inconsistency at end";
close DIFFPIPE;
# check whether a system error has occurred or return status is greater than or equal to 5
if ( $! || ($? >> 8) > 5) {
print STDERR "diff process failed with exit code ", ($? >> 8), " $!\n";
die;
}
unlink $fna,$fnb ;
}
return wantarray ? @$matchVector : $matchVector;
}
sub traverse_sequences
{
my $a = shift; # array ref
my $b = shift; # array ref
my $callbacks = shift || {};
my $keyGen = shift;
my $matchCallback = $callbacks->{'MATCH'} || sub { };
my $discardACallback = $callbacks->{'DISCARD_A'} || sub { };
my $finishedACallback = $callbacks->{'A_FINISHED'};
my $discardBCallback = $callbacks->{'DISCARD_B'} || sub { };
my $finishedBCallback = $callbacks->{'B_FINISHED'};
my $matchVector = _longestCommonSubsequence( $a, $b, $keyGen, @_ );
# Process all the lines in @$matchVector
my $lastA = $#$a;
my $lastB = $#$b;
my $bi = 0;
my $ai;
for ( $ai = 0 ; $ai <= $#$matchVector ; $ai++ )
{
my $bLine = $matchVector->[$ai];
if ( defined($bLine) ) # matched
{
&$discardBCallback( $ai, $bi++, @_ ) while $bi < $bLine;
&$matchCallback( $ai, $bi++, @_ );
}
else
{
&$discardACallback( $ai, $bi, @_ );
}
}
# The last entry (if any) processed was a match.
# $ai and $bi point just past the last matching lines in their sequences.
while ( $ai <= $lastA or $bi <= $lastB )
{
# last A?
if ( $ai == $lastA + 1 and $bi <= $lastB )
{
if ( defined($finishedACallback) )
{
&$finishedACallback( $lastA, @_ );
$finishedACallback = undef;
}
else
{
&$discardBCallback( $ai, $bi++, @_ ) while $bi <= $lastB;
}
}
# last B?
if ( $bi == $lastB + 1 and $ai <= $lastA )
{
if ( defined($finishedBCallback) )
{
&$finishedBCallback( $lastB, @_ );
$finishedBCallback = undef;
}
else
{
&$discardACallback( $ai++, $bi, @_ ) while $ai <= $lastA;
}
}
&$discardACallback( $ai++, $bi, @_ ) if $ai <= $lastA;
&$discardBCallback( $ai, $bi++, @_ ) if $bi <= $lastB;
}
return 1;
}
sub traverse_balanced
{
my $a = shift; # array ref
my $b = shift; # array ref
my $callbacks = shift || {};
my $keyGen = shift;
my $matchCallback = $callbacks->{'MATCH'} || sub { };
my $discardACallback = $callbacks->{'DISCARD_A'} || sub { };
my $discardBCallback = $callbacks->{'DISCARD_B'} || sub { };
my $changeCallback = $callbacks->{'CHANGE'};
my $matchVector = _longestCommonSubsequence( $a, $b, $keyGen, @_ );
# Process all the lines in match vector
my $lastA = $#$a;
my $lastB = $#$b;
my $bi = 0;
my $ai = 0;
my $ma = -1;
my $mb;
while (1)
{
# Find next match indices $ma and $mb
do { $ma++ } while ( $ma <= $#$matchVector && !defined $matchVector->[$ma] );
last if $ma > $#$matchVector; # end of matchVector?
$mb = $matchVector->[$ma];
# Proceed with discard a/b or change events until
# next match
while ( $ai < $ma || $bi < $mb )
{
if ( $ai < $ma && $bi < $mb )
{
# Change
if ( defined $changeCallback )
{
&$changeCallback( $ai++, $bi++, @_ );
}
else
{
&$discardACallback( $ai++, $bi, @_ );
&$discardBCallback( $ai, $bi++, @_ );
}
}
elsif ( $ai < $ma )
{
&$discardACallback( $ai++, $bi, @_ );
}
else
{
# $bi < $mb
&$discardBCallback( $ai, $bi++, @_ );
}
}
# Match
&$matchCallback( $ai++, $bi++, @_ );
}
while ( $ai <= $lastA || $bi <= $lastB )
{
if ( $ai <= $lastA && $bi <= $lastB )
{
# Change
if ( defined $changeCallback )
{
&$changeCallback( $ai++, $bi++, @_ );
}
else
{
&$discardACallback( $ai++, $bi, @_ );
&$discardBCallback( $ai, $bi++, @_ );
}
}
elsif ( $ai <= $lastA )
{
&$discardACallback( $ai++, $bi, @_ );
}
else
{
# $bi <= $lastB
&$discardBCallback( $ai, $bi++, @_ );
}
}
return 1;
}
sub LCS
{
my $a = shift; # array ref
my $matchVector = _longestCommonSubsequence( $a, @_ );
my @retval;
my $i;
for ( $i = 0 ; $i <= $#$matchVector ; $i++ )
{
if ( defined( $matchVector->[$i] ) )
{
push ( @retval, $a->[$i] );
}
}
return wantarray ? @retval : \@retval;
}
sub diff
{
my $a = shift; # array ref
my $b = shift; # array ref
my $retval = [];
my $hunk = [];
my $discard = sub { push ( @$hunk, [ '-', $_[0], $a->[ $_[0] ] ] ) };
my $add = sub { push ( @$hunk, [ '+', $_[1], $b->[ $_[1] ] ] ) };
my $match = sub { push ( @$retval, $hunk ) if scalar(@$hunk); $hunk = [] };
traverse_sequences( $a, $b,
{ MATCH => $match, DISCARD_A => $discard, DISCARD_B => $add }, @_ );
&$match();
return wantarray ? @$retval : $retval;
}
sub sdiff
{
my $a = shift; # array ref
my $b = shift; # array ref
my $retval = [];
my $discard = sub { push ( @$retval, [ '-', $a->[ $_[0] ], "" ] ) };
my $add = sub { push ( @$retval, [ '+', "", $b->[ $_[1] ] ] ) };
my $change = sub {
push ( @$retval, [ 'c', $a->[ $_[0] ], $b->[ $_[1] ] ] );
};
my $match = sub {
push ( @$retval, [ 'u', $a->[ $_[0] ], $b->[ $_[1] ] ] );
};
traverse_balanced(
$a,
$b,
{
MATCH => $match,
DISCARD_A => $discard,
DISCARD_B => $add,
CHANGE => $change,
},
@_
);
return wantarray ? @$retval : $retval;
}
1;
}
import Algorithm::Diff qw(traverse_sequences);
# End of inserted block for stand-alone version
use Getopt::Long ;
use strict ;
use warnings;
use utf8 ;
my ($algodiffversion)=split(/ /,$Algorithm::Diff::VERSION);
my ($versionstring)=<<EOF ;
This is LATEXDIFF 1.0.4 (Algorithm::Diff $Algorithm::Diff::VERSION, Perl $^V)
(c) 2004-2014 F J Tilmann
EOF
# Configuration variables: these have to be visible from the subroutines
my $MINWORDSBLOCK=3; # minimum number of tokens to form an independent block
# shorter identical blocks will be merged to the previous word
my $FLOATENV='(?:figure|table|plate)[\w\d*@]*' ; # Environments in which FL variants of defined commands are used
my $PICTUREENV='(?:picture|tikzpicture|DIFnomarkup)[\w\d*@]*' ; # Environments in which all change markup is removed
my $MATHENV='(?:equation[*]?|displaymath|DOLLARDOLLAR)[*]?' ; # Environments turning on display math mode (code also knows about \[ and \])
my $MATHREPL='displaymath'; # Environment introducing deleted maths blocks
my $MATHARRENV='(?:eqnarray|align|alignat|gather|multline|flalign)[*]?' ; # Environments turning on eqnarray math mode
my $MATHARRREPL='eqnarray*'; # Environment introducing deleted maths blocks
my $ARRENV='(?:array|[pbvBV]?matrix|smallmatrix|cases|split)'; # Environments making arrays in math mode. The underlining style does not cope well with those - as a result in-text math environments are surrounded by \mbox{ } if any of these commands is used in an inline math block
my $COUNTERCMD='(?:footnote|part|chapter|section|subsection|subsubsection|paragraph|subparagraph)'; # textcmds which are associated with a counter
# If any of these commands occur in a deleted block
# they will be succeeded by an \addtocounter{...}{-1}
# for the associated counter such that the overall numbers
# should be the same as in the new file
my @UNSAFEMATHCMD=('qedhere'); # Commands which are definitely unsafe for marking up (amsmath qedhere only tested to not work with UNDERLINE markup)
my $CITECMD=0 ; # \cite-type commands which need to be protected within an mbox in UNDERLINE and other modes using ulem; pattern simply designed to never match; will be overwritten later for selected styles
my $CITE2CMD=0; # \cite-type commands which should be reinstated in deleted blocks
my $MBOXINLINEMATH=0; # if set to 1 then surround marked-up inline maths expression with \mbox ( to get around compatibility
# problems between some maths packages and ulem package
# Markup strings
# If at all possible, do not change these as parts of the program
# depend on the actual name (particularly post-processing)
# At the very least adapt subroutine postprocess to new tokens.
my $ADDMARKOPEN='\DIFaddbegin '; # Token to mark begin of appended text
my $ADDMARKCLOSE='\DIFaddend '; # Token to mark end of appended text
my $ADDOPEN='\DIFadd{'; # To mark begin of added text passage
my $ADDCLOSE='}'; # To mark end of added text passage
my $ADDCOMMENT='DIF > '; # To mark added comment line
my $DELMARKOPEN='\DIFdelbegin '; # Token to mark begin of deleted text
my $DELMARKCLOSE='\DIFdelend '; # Token to mark end of deleted text
my $DELOPEN='\DIFdel{'; # To mark begin of deleted text passage
my $DELCLOSE='}'; # To mark end of deleted text passage
my $DELCMDOPEN='%DIFDELCMD < '; # To mark begin of deleted commands (must begin with %, i.e., be a comment
my $DELCMDCLOSE="%%%\n"; # To mark end of deleted commands (must end with a new line)
my $AUXCMD='%DIFAUXCMD' ; # follows auxiliary commands put in by latexdiff to make difference file legal
# auxiliary commands must be on a line of their own
my $DELCOMMENT='DIF < '; # To mark deleted comment line
# main local variables:
my @TEXTCMDLIST=(); # array containing patterns of commands with text arguments
my @TEXTCMDEXCL=(); # array containing patterns of commands without text arguments (if a pattern
# matches both TEXTCMDLIST and TEXTCMDEXCL it is excluded)
my @CONTEXT1CMDLIST=(); # array containing patterns of commands with text arguments (subset of text commands),
# but which cause confusion if used out of context (e.g. \caption).
# In deleted passages, the command will be disabled but its argument is marked up
# Otherwise they behave exactly like TEXTCMD's
my @CONTEXT1CMDEXCL=(); # exclude list for above, but always empty
my @CONTEXT2CMDLIST=(); # array containing patterns of commands with text arguments, but which fail or cause confusion
# if used out of context (e.g. \title). They and their arguments will be disabled in deleted
# passages
my @CONTEXT2CMDEXCL=(); # exclude list for above, but always empty
my @MATHTEXTCMDLIST=(); # treat like textcmd. If a textcmd is in deleted or added block, just wrap the
# whole content with \DIFadd or \DIFdel irrespective of content. This functionality
# is useful for pseudo commands \MATHBLOCK.. into which math environments are being
# transformed
my @MATHTEXTCMDEXCL=(); #
# Note I need to declare this with "our" instead of "my" because later in the code I have to "local"ise these
our @SAFECMDLIST=(); # array containing patterns of safe commands (which do not break when in the argument of DIFadd or DIFDEL)
our @SAFECMDEXCL=();
my ($i,$j,$l);
my ($old,$new);
my ($line);
my ($newpreamble,$oldpreamble);
my (@newpreamble,@oldpreamble,@diffpreamble,@diffbody);
my ($latexdiffpreamble);
my ($oldbody, $newbody, $diffbo);
my ($oldpost, $newpost);
my ($diffall);
# Option names
my ($type,$subtype,$floattype,$config,$preamblefile,$encoding,$nolabel,$visiblelabel,
$showpreamble,$showsafe,$showtext,$showconfig,$showall,
$replacesafe,$appendsafe,$excludesafe,
$replacetext,$appendtext,$excludetext,
$replacecontext1,$appendcontext1,
$replacecontext2,$appendcontext2,
$help,$verbose,$driver,$version,$ignorewarnings,
$enablecitmark,$disablecitmark,$allowspaces,$flatten,$debug,$earlylatexdiffpreamble); ###$disablemathmark,
# MNEMNONICS for mathmarkup
my $mathmarkup;
use constant {
OFF => 0,
WHOLE => 1,
COARSE => 2,
FINE => 3
};
my (@configlist,@labels,
@appendsafelist,@excludesafelist,
@appendtextlist,@excludetextlist,
@appendcontext1list,@appendcontext2list,
@packagelist);
my ($assign,@config);
# Hash where keys corresponds to the names of all included packages (including the documentclass as another package
# the optional arguments to the package are the values of the hash elements
my ($pkg,%packages);
# Defaults
$type='UNDERLINE';
$subtype='SAFE';
$floattype='FLOATSAFE';
$mathmarkup=COARSE;
$verbose=0;
# output debug and intermediate files, set to 0 in final distribution
$debug=0;
# insert preamble directly after documentclass - experimental feature, set to 0 in final distribution
# Note that this failed with mini example (or other files, where packages used in latexdiff preamble
# are called again with incompatible options in preamble of resulting file)
$earlylatexdiffpreamble=0;
# define character properties
sub IsNonAsciiPunct { return <<'END' # Unicode punctuation but excluding ASCII punctuation
+utf8::IsPunct
-utf8::IsASCII
END
}
sub IsNonAsciiS { return <<'END' # Unicode symbol but excluding ASCII
+utf8::IsS
-utf8::IsASCII
END
}
my %verbhash;
Getopt::Long::Configure('bundling');
GetOptions('type|t=s' => \$type,
'subtype|s=s' => \$subtype,
'floattype|f=s' => \$floattype,
'config|c=s' => \@configlist,
'preamble|p=s' => \$preamblefile,
'encoding|e=s' => \$encoding,
'label|L=s' => \@labels,
'no-label' => \$nolabel,
'visible-label' => \$visiblelabel,
'exclude-safecmd|A=s' => \@excludesafelist,
'replace-safecmd=s' => \$replacesafe,
'append-safecmd|a=s' => \@appendsafelist,
'exclude-textcmd|X=s' => \@excludetextlist,
'replace-textcmd=s' => \$replacetext,
'append-textcmd|x=s' => \@appendtextlist,
'replace-context1cmd=s' => \$replacecontext1,
'append-context1cmd=s' => \@appendcontext1list,
'replace-context2cmd=s' => \$replacecontext2,
'append-context2cmd=s' => \@appendcontext2list,
'show-preamble' => \$showpreamble,
'show-safecmd' => \$showsafe,
'show-textcmd' => \$showtext,
'show-config' => \$showconfig,
'show-all' => \$showall,
'packages=s' => \@packagelist,
'allow-spaces' => \$allowspaces,
'math-markup=s' => \$mathmarkup,
'enable-citation-markup' => \$enablecitmark,
'disable-citation-markup' => \$disablecitmark,
'verbose|V' => \$verbose,
'ignore-warnings' => \$ignorewarnings,
'driver=s'=> \$driver,
'flatten' => \$flatten,
'version' => \$version,
'help|h|H' => \$help);
if ( $help ) {
usage() ;
}
if ( $version ) {
die $versionstring ;
}
print STDERR $versionstring if $verbose;
if (defined($showall)){
$showpreamble=$showsafe=$showtext=$showconfig=1;
}
if (defined($mathmarkup)) {
$mathmarkup=~tr/a-z/A-Z/;
if ( $mathmarkup eq 'OFF' ){
$mathmarkup=OFF;
} elsif ( $mathmarkup eq 'WHOLE' ){
$mathmarkup=WHOLE;
} elsif ( $mathmarkup eq 'COARSE' ){
$mathmarkup=COARSE;
} elsif ( $mathmarkup eq 'FINE' ){
$mathmarkup=FINE;
} elsif ( $mathmarkup !~ m/^[0123]$/ ) {
die "Illegal value: ($mathmarkup) for option--math-markup. Possible values: OFF,WHOLE,COARSE,FINE,0- ";
}
# else use numerical value
}
# setting extra preamble commands
if (defined($preamblefile)) {
$latexdiffpreamble=join "\n",(extrapream($preamblefile),"");
} else {
$latexdiffpreamble=join "\n",(extrapream($type,$subtype,$floattype),"");
}
if ( defined($driver) ) {
# for changebar only
$latexdiffpreamble=~s/\[dvips\]/[$driver]/sg;
}
# setting up @SAFECMDLIST and @SAFECMDEXCL
if (defined($replacesafe)) {
init_regex_arr_ext(\@SAFECMDLIST,$replacesafe);
} else {
init_regex_arr_data(\@SAFECMDLIST, "SAFE COMMANDS");
}
foreach $appendsafe ( @appendsafelist ) {
init_regex_arr_ext(\@SAFECMDLIST, $appendsafe);
}
foreach $excludesafe ( @excludesafelist ) {
init_regex_arr_ext(\@SAFECMDEXCL, $excludesafe);
}
# setting up @TEXTCMDLIST and @TEXTCMDEXCL
if (defined($replacetext)) {
init_regex_arr_ext(\@TEXTCMDLIST,$replacetext);
} else {
init_regex_arr_data(\@TEXTCMDLIST, "TEXT COMMANDS");
}
foreach $appendtext ( @appendtextlist ) {
init_regex_arr_ext(\@TEXTCMDLIST, $appendtext);
}
foreach $excludetext ( @excludetextlist ) {
init_regex_arr_ext(\@TEXTCMDEXCL, $excludetext);
}
# setting up @CONTEXT1CMDLIST ( @CONTEXT1CMDEXCL exist but is always empty )
if (defined($replacecontext1)) {
init_regex_arr_ext(\@CONTEXT1CMDLIST,$replacecontext1);
} else {
init_regex_arr_data(\@CONTEXT1CMDLIST, "CONTEXT1 COMMANDS");
}
foreach $appendcontext1 ( @appendcontext1list ) {
init_regex_arr_ext(\@CONTEXT1CMDLIST, $appendcontext1);
}
# setting up @CONTEXT2CMDLIST ( @CONTEXT2CMDEXCL exist but is always empty )
if (defined($replacecontext2)) {
init_regex_arr_ext(\@CONTEXT2CMDLIST,$replacecontext2);
} else {
init_regex_arr_data(\@CONTEXT2CMDLIST, "CONTEXT2 COMMANDS");
}
foreach $appendcontext2 ( @appendcontext2list ) {
init_regex_arr_ext(\@CONTEXT2CMDLIST, $appendcontext2);
}
# setting configuration variables
@config=();
foreach $config ( @configlist ) {
if (-f $config || lc $config eq '/dev/null' ) {
open(FILE,$config) or die ("Couldn't open configuration file $config: $!");
while (<FILE>) {
chomp;
next if /^\s*#/ || /^\s*%/ || /^\s*$/ ;
push (@config,$_);
}
close(FILE);
}
else {
# foreach ( split(",",$config) ) {
# push @config,$_;
# }
push @config,split(",",$config)
}
}
foreach $assign ( @config ) {
$assign=~ m/\s*(\w*)\s*=\s*(\S*)\s*$/ or die "Illegal assignment $assign in configuration list (must be variable=value)";
if ( $1 eq "MINWORDSBLOCK" ) { $MINWORDSBLOCK = $2; }
elsif ( $1 eq "FLOATENV" ) { $FLOATENV = $2 ; }
elsif ( $1 eq "PICTUREENV" ) { $PICTUREENV = $2 ; }
elsif ( $1 eq "MATHENV" ) { $MATHENV = $2 ; }
elsif ( $1 eq "MATHREPL" ) { $MATHREPL = $2 ; }
elsif ( $1 eq "MATHARRENV" ) { $MATHARRENV = $2 ; }
elsif ( $1 eq "MATHARRREPL" ) { $MATHARRREPL = $2 ; }
elsif ( $1 eq "ARRENV" ) { $ARRENV = $2 ; }
elsif ( $1 eq "COUNTERCMD" ) { $COUNTERCMD = $2 ; }
else { die "Unknown variable $1 in assignment.";}
}
if ( $mathmarkup == COARSE || $mathmarkup == WHOLE ) {
push(@MATHTEXTCMDLIST,qr/^MATHBLOCK(?:$MATHENV|$MATHARRENV|SQUAREBRACKET)$/);
}
foreach $pkg ( @packagelist ) {
map { $packages{$_}="" } split(/,/,$pkg) ;
}
if ($showpreamble) {
print "\nPreamble commands:\n";
print $latexdiffpreamble ;
}
if ($showsafe) {
print "\nCommands safe within scope of $ADDOPEN $ADDCLOSE and $DELOPEN $DELCLOSE (unless excluded):\n";
print_regex_arr(@SAFECMDLIST);
print "\nCommands not safe within scope of $ADDOPEN $ADDCLOSE and $DELOPEN $DELCLOSE :\n";
print_regex_arr(@SAFECMDEXCL);
}
if ($showtext) {
print "\nCommands with last argument textual (unless excluded) and safe in every context:\n";
print_regex_arr(@TEXTCMDLIST);
print "\nContext1 commands (last argument textual, command will be disabled in deleted passages, last argument will be shown as plain text):\n";
print_regex_arr(@CONTEXT1CMDLIST);
print "\nContext2 commands (last argument textual, command and its argument will be disabled in deleted passages):\n";
print_regex_arr(@CONTEXT2CMDLIST);
print "\nExclude list of Commands with last argument not textual (overrides patterns above):\n";
print_regex_arr(@TEXTCMDEXCL);
}
if ($showconfig) {
print "Configuration variables:\n";
print "MINWORDSBLOCK=$MINWORDSBLOCK\n";
print "FLOATENV=$FLOATENV\n";
print "PICTUREENV=$PICTUREENV\n";
print "MATHENV=$MATHENV\n";
print "MATHREPL=$MATHREPL\n";
print "MATHARRENV=$MATHARRENV\n";
print "MATHARRREPL=$MATHARRREPL\n";
print "ARRENV=$ARRENV\n";
print "COUNTERCMD=$COUNTERCMD\n";
}
if ($showconfig || $showtext || $showsafe || $showpreamble) {
exit 0; }
if ( @ARGV != 2 ) {
print STDERR "2 and only 2 non-option arguments required. Write latexdiff -h to get help\n";
exit(2);
}
# Are extra spaces between command arguments permissible?
my $extraspace;
if ($allowspaces) {
$extraspace='\s*';
} else {
$extraspace='';
}
# append context lists to text lists (as text property is implied)
push @TEXTCMDLIST, @CONTEXT1CMDLIST;
push @TEXTCMDLIST, @CONTEXT2CMDLIST;
push @TEXTCMDLIST, @MATHTEXTCMDLIST if $mathmarkup==COARSE;
# internal additions to SAFECMDLIST
push(@SAFECMDLIST, qr/^QLEFTBRACE$/, qr/^QRIGHTBRACE$/);
# Patterns. These are used by some of the subroutines, too
# I can only define them down here because value of extraspace depends on an option
my $pat0 = '(?:[^{}])*';
my $pat1 = '(?:[^{}]|\{'.$pat0.'\})*';
my $pat2 = '(?:[^{}]|\{'.$pat1.'\})*';
my $pat3 = '(?:[^{}]|\{'.$pat2.'\})*';
my $pat4 = '(?:[^{}]|\{'.$pat3.'\})*';
my $pat5 = '(?:[^{}]|\{'.$pat4.'\})*';
my $pat6 = '(?:[^{}]|\{'.$pat5.'\})*';
my $brat0 = '(?:[^\[\]]|\\\[|\\\])*';
my $abrat0 = '(?:[^<>])*';
my $quotemarks = '(?:\'\')|(?:\`\`)';
my $punct='[0.,\/\'\`:;\"\?\(\)\[\]!~\p{IsNonAsciiPunct}\p{IsNonAsciiS}]';
my $number='-?\d*\.\d*';
my $mathpunct='[+=<>\-\|]';
my $and = '&';
my $coords= '[\-.,\s\d]*';
# word: sequence of letters or accents followed by letter
my $word='(?:[-\w\d*]|\\\\[\"\'\`~^][A-Za-z\*])+';
my $cmdleftright='\\\\(?:left|right|[Bb]igg?[lrm]?|middle)\s*(?:[<>()\[\]|]|\\\\(?:[|{}]|\w+))';
my $cmdoptseq='\\\\[\w\d\*]+'.$extraspace.'(?:(?:<'.$abrat0.'>|\['.$brat0.'\]|\{'. $pat6 . '\}|\(' . $coords .'\))'.$extraspace.')*';
my $backslashnl='\\\\\n';
my $oneletcmd='\\\\.\*?(?:\['.$brat0.'\]|\{'. $pat6 . '\})*';
my $math='\$(?:[^$]|\\\$)*?\$|\\\\[(](?:.|\n)*?\\\\[)]';
## the current maths command cannot cope with newline within the math expression
my $comment='%.*?\n';
my $pat=qr/(?:\A\s*)?(?:${and}|${quotemarks}|${number}|${word}|$cmdleftright|${cmdoptseq}|${math}|${backslashnl}|${oneletcmd}|${comment}|${punct}|${mathpunct}|\{|\})\s*/ ;
# now we are done setting up and can start working
my ($oldfile, $newfile) = @ARGV;
# check for existence of input files
if ( ! -e $oldfile ) {
die "Input file $oldfile does not exist.";
}
if ( ! -e $newfile ) {
die "Input file $newfile does not exist.";
}
# set the labels to be included into the file
my ($oldtime,$newtime,$oldlabel,$newlabel);
if (defined($labels[0])) {
$oldlabel=$labels[0] ;
} else {
$oldtime=localtime((stat($oldfile))[9]);
$oldlabel="$oldfile " . " "x(length($newfile)-length($oldfile)) . $oldtime;
}
if (defined($labels[1])) {
$newlabel=$labels[1] ;
} else {
$newtime=localtime((stat($newfile))[9]);
$newlabel="$newfile " . " "x(length($oldfile)-length($newfile)) . $newtime;
}
$encoding=guess_encoding($newfile) unless defined($encoding);
$encoding = "utf8" if $encoding =~ m/^utf8/i ;
if (lc($encoding) eq "utf8" ) {
binmode(STDOUT, ":utf8");
binmode(STDERR, ":utf8");
}
$old=read_file_with_encoding($oldfile,$encoding);
$new=read_file_with_encoding($newfile,$encoding);
# reset time
exetime(1);
($oldpreamble,$oldbody,$oldpost)=splitdoc($old,'\\\\begin\{document\}','\\\\end\{document\}');
($newpreamble,$newbody,$newpost)=splitdoc($new,'\\\\begin\{document\}','\\\\end\{document\}');
if ($flatten) {
$oldbody=flatten($oldbody,$oldpreamble,$oldfile,$encoding);
$newbody=flatten($newbody,$newpreamble,$newfile,$encoding);
}
my @auxlines;
if ( length $oldpreamble && length $newpreamble ) {
# pre-process preamble by looking for commands used in \maketitle (title, author, date etc commands)
# and marking up content with latexdiff markup
@auxlines=preprocess_preamble($oldpreamble,$newpreamble);
@oldpreamble = split /\n/, $oldpreamble;
@newpreamble = split /\n/, $newpreamble;
# If a command is defined in the preamble of the new file, and only uses safe commands, then it can be considered to be safe) (contribution S. Gouezel)
# Base this assessment on the new preamble
add_safe_commands($newpreamble);
# get a list of packages from preamble if not predefine
%packages=list_packages(@newpreamble) unless %packages;
### if ( %packages ) {print STDERR "DEBUG Packages: ",%packages,"\n" ;}
if (defined $packages{"hyperref"} ) {
# deleted lines should not generate or appear in link names:
print STDERR "hyperref package detected.\n" if $verbose ;
$latexdiffpreamble =~ s/\{\\DIFadd\}/{\\DIFaddtex}/g;
$latexdiffpreamble =~ s/\{\\DIFdel\}/{\\DIFdeltex}/g;
$latexdiffpreamble .= join "\n",(extrapream("HYPERREF"),"");
}
if (defined $packages{"units"} && ( $latexdiffpreamble =~ /\\RequirePackage(?:\[$brat0\])?\{ulem\}/ ) ) {
# protect inlined maths environments by surrounding with an \mbox
# this is done to get around an incompatibility between the ulem and units package
# where spaces in the argument to underlined or crossed-out \unit commands cause an error message
print STDERR "units package detected at the same time as style using ulem.\n" if $verbose ;
$MBOXINLINEMATH=1;
}
print STDERR "Differencing preamble.\n" if $verbose;
# insert dummy first line such that line count begins with line 1 (rather than perl's line 0) - just so that line numbers inserted by linediff are correct
unshift @newpreamble,'';
unshift @oldpreamble,'';
@diffpreamble = linediff(\@oldpreamble, \@newpreamble);
# remove dummy line again
shift @diffpreamble;
# add filenames, modification time and latexdiff mark
defined($nolabel) or splice @diffpreamble,1,0,
"%DIF LATEXDIFF DIFFERENCE FILE",
,"%DIF DEL $oldlabel",
"%DIF ADD $newlabel";
if ( @auxlines ) {
push @diffpreamble,"%DIF DELETED TITLE COMMANDS FOR MARKUP";
push @diffpreamble,join("\n",@auxlines);
}
if ( $earlylatexdiffpreamble) {
# insert latexdiff command directly after documentclass at beginning of preamble
# note that grep is only run for its side effect
( grep { s/^([^%]*\\documentclass.*)$/$1$latexdiffpreamble/ } @diffpreamble )==1 or die "Could not find documentclass statement in preamble";
} else {
# insert latexdiff commands at the end of preamble (default behaviour)
push @diffpreamble,$latexdiffpreamble;
}
push @diffpreamble,'\begin{document}';
}
elsif ( !length $oldpreamble && !length $newpreamble ) {
@diffpreamble=();
} else {
print STDERR "Either both texts must have preamble or neither text must have the preamble.\n";
exit(2);
}
# Special: treat all cite commands as safe except in UNDERLINE and FONTSTRIKE mode
# (there is a conflict between citation and ulem package, see
# package documentation)
# Use post-processing
# and $packages{"apacite"}!~/natbibpapa/
my ($citpat,$citpatsafe);
if ( defined $packages{"apacite"} ) {
print STDERR "DEBUG apacite citation commands\n" if $debug;
$citpatsafe=qr/^(?:mask)?(?:full|short)?cite(?:A|author|year)?(?:NP)?$/;
$citpat='(?:mask)?(?:full|short|no)?cite(?:A|author|year|meta)?(?:NP)?';
} else {
# citation command pattern for all other citation schemes
$citpatsafe=qr/^cite.*$/;
$citpat='(?:cite\w*|nocite)';
};
if ( uc($type) ne "UNDERLINE" && uc($type) ne "FONTSTRIKE" && uc($type) ne "CULINECHBAR" ) {
push (@SAFECMDLIST, $citpatsafe);
} else {
### Experimental: disable text and emph commands
push (@SAFECMDLIST, $citpatsafe) unless $disablecitmark;
push(@SAFECMDEXCL, qr/^emph$/, qr/^text..$/);
# replace \cite{..} by \mbox{\cite{..}} in added or deleted blocks in post-processing
if ( uc($subtype) eq "COLOR" or uc($subtype) eq "DVIPSCOL" ) {
# remove \cite command again from list of safe commands
pop @SAFECMDLIST;
# deleted cite commands
$CITE2CMD=$citpat unless $disablecitmark ; # \cite-type commands which should be reinstated in deleted blocks
} else {
$CITECMD=$citpat unless $disablecitmark ; # \cite commands which need to be protected within an mbox in UNDERLINE and other modes using ulem
}
}
$CITECMD=$citpat if $enablecitmark ; # as above for explicit selection
print STDERR "CITECMD:|$CITECMD|\n" if $debug;
if (defined $packages{"amsmath"} or defined $packages{"amsart"} or defined $packages{"amsbook"} ) {
print STDERR "amsmath package detected.\n" if $verbose ;
$MATHARRREPL='align*';
}
print STDERR "Preprocessing body. " if $verbose;
my ($oldleadin,$newleadin)=preprocess($oldbody,$newbody);
# run difference algorithm
@diffbody=bodydiff($oldbody, $newbody);
$diffbo=join("",@diffbody);
if ( $debug ) {
open(RAWDIFF,">","latexdiff.debug.bodydiff");
print RAWDIFF $diffbo;
close(RAWDIFF);
}
print STDERR "(",exetime()," s)\n","Postprocessing body. \n " if $verbose;
postprocess($diffbo);
$diffall =join("\n",@diffpreamble) ;
# add visible labels
if (defined($visiblelabel)) {
# Give information right after \begin{document} (or at the beginning of the text for files without preamble
### if \date command is used, add information to \date argument, otherwise give right after \begin{document}
### $diffall=~s/(\\date$extraspace(?:\[$brat0\])?$extraspace)\{($pat6)\}/$1\{$2 \\ LATEXDIFF comparison \\ Old: $oldlabel \\ New: $newlabel \}/ or
$diffbo = "\\begin{verbatim}LATEXDIFF comparison\nOld: $oldlabel\nNew: $newlabel\\end{verbatim}\n$diffbo" ;
}
$diffall .= "$newleadin$diffbo" ;
$diffall .= "\\end{document}$newpost" if length $newpreamble ;
if ( lc($encoding) ne "utf8" && lc($encoding) ne "ascii" ) {
print STDERR "Encoding output file to $encoding\n" if $verbose;
$diffall=Encode::encode($encoding,$diffall);
binmode STDOUT;
}
print $diffall;
print STDERR "(",exetime()," s)\n","Done.\n" if $verbose;
## guess_encoding(filename)
## reads the first 20 lines of filename and looks for call of inputenc package
## if found, return the option of this package (encoding), otherwise return ascii
sub guess_encoding {
my ($filename)=@_;
my ($i,$enc);
open (FH, $filename) or die("Couldn't open $filename: $!");
$i=0;
while (<FH>) {
next if /^\s*%/; # skip comment lines
if (m/\\usepackage\[(\w*?)\]\{inputenc\}/) {
close(FH);
return($1);
}
last if (++$i > 20 ); # scan at most 20 non-comment lines
}
close(FH);
return("ascii");
}
sub read_file_with_encoding {
my ($output);
my ($filename, $encoding) = @_;
if (lc($encoding) eq "utf8" ) {
open (FILE, "<:utf8",$filename) or die("Couldn't open $filename: $!");
local $/ ; # locally set record operator to undefined, ie. enable whole-file mode
$output=<FILE>;
} elsif ( lc($encoding) eq "ascii") {
open (FILE, $filename) or die("Couldn't open $filename: $!");
local $/ ; # locally set record operator to undefined, ie. enable whole-file mode
$output=<FILE>;
} else {
require Encode;
open (FILE, "<",$filename) or die("Couldn't open $filename: $!");
local $/ ; # locally set record operator to undefined, ie. enable whole-file mode
$output=<FILE>;
print STDERR "Converting $filename from $encoding to utf8\n" if $verbose;
$output=Encode::decode($encoding,$output);
}
close FILE;
if ($^O eq "linux" ) {
$output =~ s/\r\n/\n/g ;
}
return $output;
}
# %packages=list_packages(@preamble)
# scans the arguments for \documentclass,\RequirePackage and \usepackage statements and constructs a hash
# whose keys are the included packages, and whose values are the associated optional arguments
sub list_packages {
my (@preamble)=@_;
my %packages=();
foreach $line ( @preamble ) {
# get rid of comments
$line=~s/(?<!\\)%.*$// ;
if ( $line =~ m/\\(?:documentclass|usepackage|RequirePackage)(?:\[(.+?)\])?\{(.*?)\}/ ) {
# print STDERR "Found something: |$line|\n";
if (defined($1)) {
$packages{$2}=$1;
} else {
$packages{$2}="";
}
}
}
return (%packages);
}
# Subroutine add_safe_commands modified from version provided by S. Gouezel
# add_safe_commands($preamble)
# scans the argument for \newcommand and \DeclareMathOperator,
# and adds the created commands which are clearly safe to @SAFECMDLIST
sub add_safe_commands {
my ($preamble)=@_;
my $added_command = 1;
$preamble=~s/(?<!\\)%.*$//mg ;
while ($added_command) {
$added_command = 0;
# get rid of comments
my $to_test = "";
# test for \DeclareMathOperator{\foo}{myoperator}
while ( $preamble =~ m/\DeclareMathOperator\s*\*?\{\\(\w*?)\}/osg) {
$to_test=$1;
if ($to_test ne "" and not iscmd($to_test,\@SAFECMDLIST,\@SAFECMDEXCL) and not iscmd($to_test, \@SAFECMDEXCL, [])) {
# one should add $to_test to the list of safe commands.
init_regex_arr_ext(\@SAFECMDLIST, $to_test);
$added_command = 1;
print STDERR "Adding $to_test to the list of safe commands\n" if $verbose;
}
}
while ( $preamble =~ m/\\(?:new|renew|provide)command\s*{\\(\w*)\}(?:|\[\d*\])\s*\{(${pat6})\}/osg ) {
my $maybe_to_test = $1;
my $should_be_safe = $2;
my $success = 0;
# test if all latex commands inside it are safe
$success = 1;
if ($should_be_safe =~ m/\\\\/) {
$success = 0;
} else {
while ($should_be_safe =~ m/\\(\w+)/g) {
$success = 0 unless iscmd($1,\@SAFECMDLIST,\@SAFECMDEXCL); ### or $1 eq "";
}
}
### }
$to_test = $maybe_to_test if $success;
if ($to_test ne "" and not iscmd($to_test,\@SAFECMDLIST,\@SAFECMDEXCL) and not iscmd($to_test, \@SAFECMDEXCL, [])) {
# # one should add $to_test to the list of safe commands.
init_regex_arr_ext(\@SAFECMDLIST, $to_test);
$added_command = 1;
print STDERR "Adding $to_test to the list of safe commands\n" if $verbose;
}
}
}
}
# flatten($text,$preamble,$filename,$encoding)
# expands \input and \include commands within text
# expands \bibliography command with corresponding bbl file if available
# expands \subfile command (from subfiles package - not part of standard text distribution)
# preamble is scanned for includeonly commands
# encoding is the encoding
sub flatten {
my ($text,$preamble,$filename,$encoding)=@_;
my ($includeonly,$dirname,$fname,$newpage,$replacement,$begline,$bblfile,$subfile);
my ($subpreamble,$subbody,$subpost);
require File::Basename ;
require File::Spec ;
$dirname = File::Basename::dirname($filename);
$bblfile = $filename;
$bblfile=~s/\.tex$//;
$bblfile.=".bbl";
if ( ($includeonly) = ($preamble =~ m/\\includeonly{(.*?)}/ ) ) {
$includeonly =~ s/,/|/g;
} else {
$includeonly = '.*?';
}
print STDERR "DEBUG: includeonly $includeonly\n" if $debug;
# recursively replace \\input and \\include files
$text=~s/(^(?:[^%\n]|\\%)*)\\input{(.*?)}|\\include{(${includeonly}(?:\.tex)?)}/{
$fname = $2 if defined($2) ;
$fname = $3 if defined($3) ;
# # add tex extension unless there is a three letter extension already
$fname .= ".tex" unless $fname =~ m|\.\w{3}|;
print STDERR "DEBUG Beg of line match |$1|\n" if defined($1) && $debug ;
print STDERR "Include file $fname\n" if $verbose;
print STDERR "DEBUG looking for file ",File::Spec->catfile($dirname,$fname), "\n" if $debug;
# content of file becomes replacement value (use recursion), add \newpage if the command was include
###$replacement=read_file_with_encoding(File::Spec->catfile($dirname,$fname), $encoding) or die "Couldn't find file ",File::Spec->catfile($dirname,$fname),": $!";
$replacement=flatten(read_file_with_encoding(File::Spec->catfile($dirname,$fname), $encoding), $preamble,$filename,$encoding) or die "Couldn't find file ",File::Spec->catfile($dirname,$fname),": $!";
# \include always starts a new page; use explicit \newpage command to simulate this
$begline=(defined($1)? $1 : "") ;
$newpage=(defined($3)? " \\newpage " : "") ;
"$begline$newpage$replacement$newpage";
}/exgm;
# replace bibliography with bbl file if it exists
$text=~s/(^(?:[^%\n]|\\%)*)\\bibliography{(.*?)}/{
if ( -f $bblfile ){
$replacement=read_file_with_encoding(File::Spec->catfile($bblfile), $encoding);
} else {
warn "Bibliography file $bblfile cannot be found. No flattening of \\bibliography done. Run bibtex on old and new files first";
$replacement="\\bibliography{$2}";
}
$begline=(defined($1)? $1 : "") ;
"$begline$replacement";
}/exgm;
# replace subfile with contents (subfile package)
$text=~s/(^(?:[^%\n]|\\%)*)\\subfile{(.*?)}/{
$fname = $2;
# # add tex extension unless there is a three letter extension already
$fname .= ".tex" unless $fname =~ m|\.\w{3}|;
print STDERR "DEBUG Beg of line match |$1|\n" if defined($1) && $debug ;
print STDERR "Include file as subfile $fname\n" if $verbose;
print STDERR "DEBUG looking for file ",File::Spec->catfile($dirname,$fname), "\n" if $debug;
# content of file becomes replacement value (use recursion)
# now strip away everything outside and including \begin{document} and \end{document} pair#
# # note: no checking for comments is made
$subfile=read_file_with_encoding(File::Spec->catfile($dirname,$fname), $encoding) or die "Couldn't find file ",File::Spec->catfile($dirname,$fname),": $!";
($subpreamble,$subbody,$subpost)=splitdoc($subfile,'\\\\begin\{document\}','\\\\end\{document\}');
$replacement=flatten($subbody, $preamble,$filename,$encoding);
$begline=(defined($1)? $1 : "") ;
"$begline$replacement";
}/exgm;
return($text);
}
# print_regex_arr(@arr)
# prints regex array without x-ism expansion put in by pearl to stdout
sub print_regex_arr {
my $dumstring;
$dumstring = join(" ",@_); # PERL generates string (?-xism:^ref$) for quoted refex ^ref$
$dumstring =~ s/\(\?-xism:\^(.*?)\$\)/$1/g; # remove string and ^,$ marks before output
print $dumstring,"\n";
}
# @lines=extrapream($type)
# reads line from appendix (end of file after __END__ token)
sub extrapream {
my $type;
my @retval=("%DIF PREAMBLE EXTENSION ADDED BY LATEXDIFF") ;
my ($copy);
while (@_) {
$copy=0;
$type=shift ;
if ( -f $type || lc $type eq '/dev/null' ) {
open (FILE,$type) or die "Cannot open preamble file $type: $!";
print STDERR "Reading preamble file $type\n" if $verbose ;
while (<FILE>) {
chomp ;
if ( $_ =~ m/%DIF PREAMBLE/ ) {
push (@retval,"$_");
} else {
push (@retval,"$_ %DIF PREAMBLE");
}
}
}
else { # not (-f $type)
$type=uc($type); # upcase argument
print STDERR "Preamble Internal Type $type\n" if $verbose;
while (<DATA>) {
if ( m/^%DIF $type/ ) {
$copy=1; }
elsif ( m/^%DIF END $type/ ) {
last; }
chomp;
push (@retval,"$_ %DIF PREAMBLE") if $copy;
}
if ( $copy == 0 ) {
print STDERR "\nPreamble style $type not implemented.\n";
print STDERR "Write latexdiff -h to get help with available styles\n";
exit(2);
}
seek DATA,0,0; # rewind DATA handle to file begin
}
}
push (@retval,"%DIF END PREAMBLE EXTENSION ADDED BY LATEXDIFF") ;
return @retval;
}
# ($part1,$part2,$part3)=splitdoc($text,$word1,$word2)
# splits $text into 3 parts at $word1 and $word2.
# if neither $word1 nor $word2 exist, $part1 and $part3 are empty, $part2 is $text
# If only $word1 or $word2 exist but not the other, output an error message.
# NB this version avoids $` and $' for performance reason although it only makes a tiny difference
# (in one test gain a tenth of a second for a 30s run)
sub splitdoc {
my ($text,$word1,$word2)=@_;
my ($part1,$part2,$part3)=("","","");
my ($rest,$pos);
if ( $text =~ m/(^[^%]*)($word1)/mg ) {
$pos=pos $text;
$part1=substr($text,0,$pos-length($2));
$rest=substr($text,$pos);
if ( $rest =~ m/(^[^%]*)($word2)/mg ) {
$pos=pos $rest;
$part2=substr($rest,0,$pos-length($2));
$part3=substr($rest,$pos);
}
else {
die "$word1 and $word2 not in the correct order or not present as a pair." ;
}
} else {
$part2=$text;
die "$word2 present but not $word1." if ( $text =~ m/(^[^%]*)$word2/ms );
}
return ($part1,$part2,$part3);
}
# bodydiff($old,$new)
sub bodydiff {
my ($oldwords, $newwords) = @_;
my @retwords;
print STDERR "(",exetime()," s)\n","Splitting into latex tokens \n" if $verbose;
print STDERR "Parsing $oldfile \n" if $verbose;
my @oldwords = splitlatex($oldwords);
print STDERR "Parsing $newfile \n" if $verbose;
my @newwords = splitlatex($newwords);
if ( $debug ) {
open(TOKENOLD,">","latexdiff.debug.tokenold");
print TOKENOLD join("***\n",@oldwords);
close(TOKENOLD);
open(TOKENNEW,">","latexdiff.debug.tokennew");
print TOKENNEW join("***\n",@newwords);
close(TOKENNEW);
}
print STDERR "(",exetime()," s)\n","Pass 1: Expanding text commands and merging isolated identities with changed blocks " if $verbose;
pass1(\@oldwords, \@newwords);
print STDERR "(",exetime()," s)\n","Pass 2: inserting DIF tokens and mark up. " if $verbose;
if ( $debug ) {
open(TOKENOLD,">","latexdiff.debug.tokenold2.tex");
print TOKENOLD join("***\n",@oldwords);
close(TOKENOLD);
open(TOKENNEW,">","latexdiff.debug.tokennew2.tex");
print TOKENNEW join("***\n",@newwords);
close(TOKENNEW);
}
@retwords=pass2(\@oldwords, \@newwords);
return(@retwords);
}
# @words=splitlatex($string)
# split string according to latex rules
# Each element of words is either
# a word (including trailing spaces and punctuation)
# a latex command
sub splitlatex {
my ($string) = @_ ;
# if input is empty, return empty list
length($string)>0 or return ();
my @retval=($string =~ m/$pat/osg);
if (length($string) != length(join("",@retval))) {
print STDERR "\nWARNING: Inconsistency in length of input string and parsed string:\n This often indicates faulty or non-standard latex code.\n In many cases you can ignore this and the following warning messages.\n Note that character numbers in the following are counted beginning after \\begin{document} and are only approximate." unless $ignorewarnings;
print STDERR "DEBUG Original length ",length($string)," Parsed length ",length(join("",@retval)),"\n" if $debug;
print STDERR "DEBUG Input string: |$string|\n" if (length($string)<500) && $debug;
print STDERR "DEBUG Token parsing: |",join("+",@retval),"|\n" if (length($string)<500) && $debug ;
@retval=();
# slow way only do this if other m//sg method fails
my $last = 0;
while ( $string =~ m/$pat/osg ) {
my $match=$&;
if ($last + length $& != pos $string ) {
my $pos=pos($string);
my $offset=30<$last ? 30 : $last;
my $dum=substr($string,$last-$offset,$pos-$last+2*$offset);
my $dum1=$dum;
my $cnt=$#retval;
my $i;
$dum1 =~ s/\n/ /g;
unless ($ignorewarnings) {
print STDERR "\n$dum1\n";
print STDERR " " x 30,"^" x ($pos-$last)," " x 30,"\n";
print STDERR "Missing characters near word " . (scalar @retval) . " character index: " . $last . "-" . pos($string) . " Length: " . length($match) . " Match: |$match| (expected match marked above).\n";
}
# put in missing characters `by hand'
push (@retval, substr($dum,$offset,$pos-$last-length($match)));
# Note: there seems to be a bug in substr with utf8 that made the following line output substr which were too long,
# using dum instead appears to work
# push (@retval, substr($string,$last, pos($string)-$last-length($match)));
}
push (@retval, $match);
$last=pos $string;
}
}
return @retval;
}
# pass1( \@seq1,\@seq2)
# Look for differences between seq1 and seq2.
# Where an common-subsequence block is flanked by deleted or appended blocks,
# and is shorter than $MINWORDSBLOCK words it is appended
# to the last deleted or appended word. If the block contains tokens other than words
# or punctuation it is not merged.
# Deleted or appended block consisting of words and safe commands only are
# also merged, to prevent break-up in pass2 (after previous isolated words have been removed)
# If there are commands with textual arguments (e.g. \caption) both in corresponding
# appended and deleted blocks split them such that the command and opening bracket
# are one token, then the rest is split up following standard rules, and the closing
# bracket is a separate token, ie. turn
# "\caption{This is a textual argument}" into
# ("\caption{","This ","is ","a ","textual ","argument","}")
# No return value. Destructively changes sequences
sub pass1 {
my $seq1 = shift ;
my $seq2 = shift ;
my $len1 = scalar @$seq1;
my $len2 = scalar @$seq2;
my $wpat=qr/^(?:[a-zA-Z.,'`:;?()!]*)[\s~]*$/; #'
my ($last1,$last2)=(-1,-1) ;
my $cnt=0;
my $block=[];
my $addblock=[];
my $delblock=[];
my $todo=[];
my $instruction=[];
my $i;
my (@delmid,@addmid,@dummy);
my ($addcmds,$delcmds,$matchindex);
my ($addtextblocks,$deltextblocks);
my ($addtokcnt,$deltokcnt,$mattokcnt)=(0,0,0);
my ($addblkcnt,$delblkcnt,$matblkcnt)=(0,0,0);
my $adddiscard = sub {
if ($cnt > 0 ) {
$matblkcnt++;
# just after an unchanged block
# print STDERR "Unchanged block $cnt, $last1,$last2 \n";
if ($cnt < $MINWORDSBLOCK
&& $cnt==scalar (
grep { /^$wpat/ || ( /^\\([\w\d\*]+)((?:\[$brat0\]|\{$pat6\})*)/o
&& iscmd($1,\@SAFECMDLIST,\@SAFECMDEXCL)
&& scalar(@dummy=split(" ",$2))<3 ) }
@$block) ) {
# merge identical blocks shorter than $MINWORDSBLOCK
# and only containing ordinary words
# with preceding different word
# We cannot carry out this merging immediately as this
# would change the index numbers of seq1 and seq2 and confuse
# the algorithm, instead we store in @$todo where we have to merge
push(@$todo, [ $last1,$last2,$cnt,@$block ]);
}
$block = [];
$cnt=0; $last1=-1; $last2=-1;
}
};
my $discard=sub { $deltokcnt++;
&$adddiscard; #($_[0],$_[1]);
push(@$delblock,[ $seq1->[$_[0]],$_[0] ]);
$last1=$_[0] };
my $add = sub { $addtokcnt++;
&$adddiscard; #($_[0],$_[1]);
push(@$addblock,[ $seq2->[$_[1]],$_[1] ]);
$last2=$_[1] };
my $match = sub { $mattokcnt++;
if ($cnt==0) { # first word of matching sequence after changed sequence or at beginning of word sequence
$deltextblocks = extracttextblocks($delblock);
$delblkcnt++ if scalar @$delblock;
$addtextblocks = extracttextblocks($addblock);
$addblkcnt++ if scalar @$addblock;
$delcmds = extractcommands($delblock);
$addcmds = extractcommands($addblock);
# keygen(third argument of _longestCommonSubsequence) implies to sort on command (0th elements of $addcmd elements)
# the calling format for longestCommonSubsequence has changed between versions of
# Algorithm::Diff so we need to check which one we are using
if ( $algodiffversion > 1.15 ) {
### Algorithm::Diff 1.19
$matchindex=Algorithm::Diff::_longestCommonSubsequence($delcmds,$addcmds, 0, sub { $_[0]->[0] } );
} else {
### Algorithm::Diff 1.15
$matchindex=Algorithm::Diff::_longestCommonSubsequence($delcmds,$addcmds, sub { $_[0]->[0] } );
}
for ($i=0 ; $i<=$#$matchindex ; $i++) {
if (defined($matchindex->[$i])){
$j=$matchindex->[$i];
@delmid=splitlatex($delcmds->[$i][3]);
@addmid=splitlatex($addcmds->[$j][3]);
while (scalar(@$deltextblocks) && $deltextblocks->[0][0]<$delcmds->[$i][1]) {
my ($index,$block,$cnt)=@{ shift(@$deltextblocks) };
push(@$todo, [$index,-1,$cnt,@$block]);
}
push(@$todo, [ $delcmds->[$i][1],-1,-1,$delcmds->[$i][2],@delmid,$delcmds->[$i][4]]);
while (scalar(@$addtextblocks) && $addtextblocks->[0][0]<$addcmds->[$j][1]) {
my ($index,$block,$cnt)=@{ shift(@$addtextblocks) };
push(@$todo, [-1,$index,$cnt,@$block]);
}
push(@$todo, [ -1,$addcmds->[$j][1],-1,$addcmds->[$j][2],@addmid,$addcmds->[$j][4]]);
}
}
# mop up remaining textblocks
while (scalar(@$deltextblocks)) {
my ($index,$block,$cnt)=@{ shift(@$deltextblocks) } ;
push(@$todo, [$index,-1,$cnt,@$block]);
}
while (scalar(@$addtextblocks)) {
my ($index,$block,$cnt)=@{ shift(@$addtextblocks) };
push(@$todo, [-1,$index,$cnt,@$block]);
}
$addblock=[];
$delblock=[];
}
push(@$block,$seq2->[$_[1]]);
$cnt++ };
my $keyfunc = sub { join(" ",split(" ",shift())) };
traverse_sequences($seq1,$seq2, { MATCH=>$match, DISCARD_A=>$discard, DISCARD_B=>$add }, $keyfunc );
# now carry out the merging/splitting. Refer to elements relative from
# the end (with negative indices) as these offsets don't change before the instruction is executed
# cnt>0: merged small unchanged groups with previous changed blocks
# cnt==-1: split textual commands into components
foreach $instruction ( @$todo) {
($last1,$last2,$cnt,@$block)=@$instruction ;
if ($cnt>=0) {
splice(@$seq1,$last1-$len1,1+$cnt,join("",$seq1->[$last1-$len1],@$block)) if $last1>=0;
splice(@$seq2,$last2-$len2,1+$cnt,join("",$seq2->[$last2-$len2],@$block)) if $last2>=0;
} else {
splice(@$seq1,$last1-$len1,1,@$block) if $last1>=0;
splice(@$seq2,$last2-$len2,1,@$block) if $last2>=0;
}
}
if ($verbose) {
print STDERR "\n";
print STDERR " $mattokcnt matching tokens in $matblkcnt blocks.\n";
print STDERR " $deltokcnt discarded tokens in $delblkcnt blocks.\n";
print STDERR " $addtokcnt appended tokens in $addblkcnt blocks.\n";
}
}
# extracttextblocks(\@blockindex)
# $blockindex has the following format
# [ [ token1, index1 ], [token2, index2],.. ]
# where index refers to the index in the original old or new word sequence
# Returns: reference to an array of the form
# [[ $index, $textblock, $cnt ], ..
# where $index index of block to be merged
# $textblock contains all the words to be merged with the word at $index (but does not contain this word)
# $cnt is length of block
#
# requires: iscmd
#
sub extracttextblocks {
my $block=shift;
my ($i,$token,$index);
my $textblock=[];
my $last=-1;
my $wpat=qr/^(?:[a-zA-Z.,'`:;?()!]*)[\s~]*$/; #'
my $retval=[];
for ($i=0;$i< scalar @$block;$i++) {
($token,$index)=@{ $block->[$i] };
# store pure text blocks
if ($token =~ /$wpat/ || ( $token =~/^\\([\w\d\*]+)((?:${extraspace}\[$brat0\]${extraspace}|${extraspace}\{$pat6\})*)/o
&& iscmd($1,\@SAFECMDLIST,\@SAFECMDEXCL)
&& !iscmd($1,\@TEXTCMDLIST,\@TEXTCMDEXCL))) {
# we have text or a command which can be treated as text
if ($last<0) {
# new pure-text block
$last=$index;
} else {
# add to pure-text block
push(@$textblock, $token);
}
} else {
# it is not text
if (scalar(@$textblock)) {
push(@$retval,[ $last, $textblock, scalar(@$textblock) ]);
}
$textblock=[];
$last=-1;
}
}
# finish processing a possibly unfinished block before returning
if (scalar(@$textblock)) {
push(@$retval,[ $last, $textblock, scalar(@$textblock) ]);
}
return($retval)
}
# extractcommands( \@blockindex )
# $blockindex has the following format
# [ [ token1, index1 ], [token2, index2],.. ]
# where index refers to the index in the original old or new word sequence
# Returns: reference to an array of the form
# [ [ "\cmd1", index, "\cmd1[optarg]{arg1}{", "arg2" ,"} " ],..
# where index is just taken from input array
# command must have a textual argument as last argument
#
# requires: iscmd
#
sub extractcommands {
my $block=shift;
my ($i,$token,$index,$cmd,$open,$mid,$closing);
my $retval=[];
for ($i=0;$i< scalar @$block;$i++) {
($token,$index)=@{ $block->[$i] };
# check if token is an alphanumeric command sequence with at least one non-optional argument
# \cmd[...]{...}{last argument}
# Capturing in the following results in these associations
# $1: \cmd[...]{...}{
# $2: \cmd
# $3: last argument
# $4: } + trailing spaces
if ( ( $token =~ m/^(\\([\w\d\*]+)(?:${extraspace}\[$brat0\]|${extraspace}\{$pat6\})*${extraspace}\{)($pat6)(\}\s*)$/so )
&& iscmd($2,\@TEXTCMDLIST,\@TEXTCMDEXCL) ) {
# push(@$retval,[ $2,$index,$1,$3,$4 ]);
($cmd,$open,$mid,$closing) = ($2,$1,$3,$4) ;
$closing =~ s/\}/\\RIGHTBRACE/ ;
push(@$retval,[ $cmd,$index,$open,$mid,$closing ]);
}
}
return $retval;
}
# iscmd($cmd,\@regexarray,\@regexexcl) checks
# return 1 if $cmd matches any of the patterns in the
# array $@regexarray, and none of the patterns in \@regexexcl, otherwise return 0
sub iscmd {
my ($cmd,$regexar,$regexexcl)=@_;
my ($ret)=0;
foreach $pat ( @$regexar ) {
if ( $cmd =~ m/^${pat}$/ ) {
$ret=1 ;
last;
}
}
return 0 unless $ret;
foreach $pat ( @$regexexcl ) {
return 0 if ( $cmd =~ m/^${pat}$/ );
}
return 1;
}
# pass2( \@seq1,\@seq2)
# Look for differences between seq1 and seq2.
# Mark begin and end of deleted and appended sequences with tags $DELOPEN and $DELCLOSE
# and $ADDOPEN and $ADDCLOSE, respectively, however exclude { } & and all comands, unless
# they match an element of the whitelist (SAFECMD)
# For words in TEXTCMD but not in SAFECMD, enclose interior with $ADDOPEN and $ADDCLOSE brackets
# Deleted comment lines are marked with %DIF <
# Added comment lines are marked with %DIF >
sub pass2 {
my $seq1 = shift ;
my $seq2 = shift ;
my ($addtokcnt,$deltokcnt,$mattokcnt)=(0,0,0);
my ($addblkcnt,$delblkcnt,$matblkcnt)=(0,0,0);
my $retval = [];
my $delhunk = [];
my $addhunk = [];
my $discard = sub { $deltokcnt++;
push ( @$delhunk, $seq1->[$_[0]]) };
my $add = sub { $addtokcnt++;
push ( @$addhunk, $seq2->[$_[1]]) };
my $match = sub { $mattokcnt++;
if ( scalar @$delhunk ) {
$delblkcnt++;
# mark up changes, but comment out commands
push @$retval,marktags($DELMARKOPEN,$DELMARKCLOSE,$DELOPEN,$DELCLOSE,$DELCMDOPEN,$DELCMDCLOSE,$DELCOMMENT,$delhunk);
$delhunk = [];
}
if ( scalar @$addhunk ) {
$addblkcnt++;
# we mark up changes, but simply quote commands
push @$retval,marktags($ADDMARKOPEN,$ADDMARKCLOSE,$ADDOPEN,$ADDCLOSE,"","",$ADDCOMMENT,$addhunk);
$addhunk = [];
}
push(@$retval,$seq2->[$_[1]]) };
my $keyfunc = sub { join(" ",split(" ",shift())) };
traverse_sequences($seq1,$seq2, { MATCH=>$match, DISCARD_A=>$discard, DISCARD_B=>$add }, $keyfunc );
# clear up unprocessed hunks
push @$retval,marktags($DELMARKOPEN,$DELMARKCLOSE,$DELOPEN,$DELCLOSE,$DELCMDOPEN,$DELCMDCLOSE,$DELCOMMENT,$delhunk) if scalar @$delhunk;
push @$retval,marktags($ADDMARKOPEN,$ADDMARKCLOSE,$ADDOPEN,$ADDCLOSE,"","",$ADDCOMMENT,$addhunk) if scalar @$addhunk;
if ($verbose) {
print STDERR "\n";
print STDERR " $mattokcnt matching tokens. \n";
print STDERR " $deltokcnt discarded tokens in $delblkcnt blocks.\n";
print STDERR " $addtokcnt appended tokens in $addblkcnt blocks.\n";
}
return(@$retval);
}
# marktags($openmark,$closemark,$open,$close,$opencmd,$closecmd,$comment,\@block)
# returns ($openmark,$open,$block,$close,$closemark) if @block only contains no commands (except white-listed ones),
# braces, ampersands, or comments
# mark comments with $comment
# exclude all other exceptions from scope of open, close like this
# ($openmark, $open,...,$close, $opencmd,command, command,$closecmd, $open, ..., $close, $closemark)
# If $opencmd begins with "%" marktags assumes it is operating on a deleted block, otherwise on an added block
sub marktags {
my ($openmark,$closemark,$open,$close,$opencmd,$closecmd,$comment,$block)=@_;
my $word;
my (@argtext);
my $retval=[];
my $noncomment=0;
my $cmd=-1; # -1 at beginning 0: last token written is a ordinary word
# 1: last token written is a command
# for keeping track whether we are just in a command sequence or in a word sequence
my $cmdcomment= ($opencmd =~ m/^%/); # Flag to indicate whether opencmd is a comment (i.e. if we intend to simply comment out changed commands)
my ($command,$commandword,$closingbracket) ; # temporary variables needed below to remember sub-pattern matches
# split this block to flatten out sequences joined in pass1
@$block=splitlatex(join "",@$block);
foreach (@$block) {
$word=$_;
if ( $word =~ s/^%/%$comment/ ) {
# a comment
if ($cmd==1) {
push (@$retval,$closecmd) ;
$cmd=-1;
}
push (@$retval,$word);
next;
}
if (! $noncomment) {
push (@$retval,$openmark);
$noncomment=1;
}
# negative lookahead pattern (?!) in second clause is put in to avoid mathcing \( .. \) patterns
# also note that second pattern will match \\
# Note: the second pattern should really be $word =~ /^\\(?!\()(\\|[\w*@]+)/, ie * replaced by +
# and then all commands \" \' etc declared safe. But as I don't have a complete list of one letter
# commands, and nobody has complained so far, I will eave this as is
if ( $word =~ /^[&{}\[\]]/ || ( $word =~ /^\\(?!\()(\\|[\w*@]*)/ && !iscmd($1,\@SAFECMDLIST,\@SAFECMDEXCL)) ) {
# word is a command or other significant token (not in SAFECMDLIST)
## same conditions as in subroutine extractcommand:
# check if token is an alphanumeric command sequence with at least one non-optional argument
# \cmd[...]{...}{last argument}
# Capturing in the following results in these associations
# $1: \cmd[...]{...}{
# $2: cmd
# $3: last argument
# $4: } + trailing spaces
### pre-0.3 if ( ( $token =~ m/^(\\([\w\d\*]+)(?:\[$brat0\]|\{$pat6\})*\{)($pat6)(\}\s*)$/so )
if ( ( $word =~ m/^(\\([\w\d\*]+)(?:${extraspace}\[$brat0\]|${extraspace}\{$pat6\})*${extraspace}\{)($pat6)(\}\s*)$/so )
&& (iscmd($2,\@TEXTCMDLIST,\@TEXTCMDEXCL)|| iscmd($2,\@MATHTEXTCMDLIST,\@MATHTEXTCMDEXCL))
&& ( !$cmdcomment || !iscmd($2,\@CONTEXT2CMDLIST, \@CONTEXT2CMDEXCL) ) ) {
# Condition 1: word is a command? - if yes, $1,$2,.. will be set as above
# Condition 2: word is a text command - we mark up the interior of the word. There is a separate check for MATHTEXTCMDLIST
# because for $mathmarkup=WHOLE, the commands should not be split in pass1 (ie. math mode commands are not in
# TEXTCMDLIST, but the interior of MATHTEXT commands should be highlighted in both deleted and added blocks
# Condition 3: But if we are in a deleted block ($cmdcomment=1) and
# $2 (the command) is in context2, just treat it as an ordinary command (i.e. comment it open with $opencmd)
# Because we do not want to disable this command
# here we do not use $opencmd and $closecmd($opencmd is empty)
if ($cmd==1) {
push (@$retval,$closecmd) ;
} elsif ($cmd==0) {
push (@$retval,$close) ;
}
$command=$1; $commandword=$2; $closingbracket=$4;
@argtext=splitlatex($3); # split textual argument into tokens
# and mark it up (but we do not need openmark and closemark)
# insert command with initial arguments, marked-up final argument, and closing bracket
if ( $cmdcomment && iscmd($commandword,\@CONTEXT1CMDLIST, \@CONTEXT1CMDEXCL) ) {
# context1cmd in a deleted environment; delete command itself but keep last argument, marked up
push (@$retval,$opencmd);
$command =~ s/\n/\n${opencmd}/sg ; # repeat opencmd at the beginning of each line
# argument, note that the additional comment character is included
# to suppress linebreak after opening parentheses, which is important
# for latexrevise
push (@$retval,$command,"%\n{$AUXCMD\n",marktags("","",$open,$close,$opencmd,$closecmd,$comment,\@argtext),$closingbracket);
} elsif ( iscmd($commandword,,\@MATHTEXTCMDLIST, \@MATHTEXTCMDEXCL) ) {
# MATHBLOCK pseudo command: consider all commands safe, except & and \\
# Keep these commands even in deleted blocks, hence set $opencmd and $closecmd (5th and 6th argument of marktags) to
# ""
local @SAFECMDLIST=(".*");
local @SAFECMDEXCL=('\\','\\\\',@UNSAFEMATHCMD);
push(@$retval,$command,marktags("","",$open,$close,"","",$comment,\@argtext)#@argtext
,$closingbracket);
} else {
# normal textcmd or context1cmd in an added block
push (@$retval,$command,marktags("","",$open,$close,$opencmd,$closecmd,$comment,\@argtext),$closingbracket);
}
push (@$retval,$AUXCMD,"\n") if $cmdcomment ;
$cmd=-1 ;
} else {
# ordinary command
push (@$retval,$opencmd) if $cmd==-1 ;
push (@$retval,$close,$opencmd) if $cmd==0 ;
$word =~ s/\n/\n${opencmd}/sg if $cmdcomment ; # if opencmd is a comment, repeat this at the beginning of every line
push (@$retval,$word);
$cmd=1;
}
} else {
# just an ordinary word or word in SAFECMD
push (@$retval,$open) if $cmd==-1 ;
push (@$retval,$closecmd,$open) if $cmd==1 ;
push (@$retval,$word);
$cmd=0;
}
}
push (@$retval,$close) if $cmd==0;
push (@$retval,$closecmd) if $cmd==1;
push (@$retval,$closemark) if ($noncomment);
return @$retval;
}
# preprocess($string, ..)
# carry out the following pre-processing steps for all arguments:
# 1. Remove leading white-space
# Change \{ to \QLEFTBRACE and \} to \QRIGHTBRACE
# #. Change {,} in comments to \CLEFTBRACE, \CRIGHTBRACE
# 2. mark all first empty line (in block of several) with \PAR tokens
# 3. Convert all '\%' into '\PERCENTAGE ' and all '\$' into \DOLLAR to make parsing regular expressions easier
# 4. Convert all \verb|some verbatim text| commands (where | can be an arbitrary character)
# into \verb{hash}
# 5. Convert \begin{verbatim} some verbatim text \end{verbatim} into \verbatim{hash}
# 6. Convert _n into \SUBSCRIPTNB{n} and _{nnn} into \SUBSCRIPT{nn}
# 7. Convert ^n into \SUPERSCRIPTNB{n} and ^{nnn} into \SUPERSCRIPT{nn}
# 8. a. Convert $$ $$ into \begin{DOLLARDOLLAR} \end{DOLLARDOLLAR}
# b. Convert \[ \] into \begin{SQUAREBRACKET} \end{SQUAREBRACKET}
# 9. Convert all picture environmentent (\begin{PICTUREENV} .. \end{PICTUREENV} \PICTUREBLOCKenv
# For --block-math-markup option -convert all \begin{MATH} .. \end{MATH}
# into \MATHBLOCKmath{...} commands, where MATH/math is any valid math environment
# 10. Add final token STOP to the very end. This is put in because the algorithm works better if the last token is identical. This is removed again in postprocessing.
#
# NB: step 6 and 7 is likely to convert some "_" inappropriately, e.g. in file
# names or labels but it does not matter because they are converted back in the postprocessing step
# Returns: leading white space removed in step 1
sub preprocess {
my @leadin=() ;
for (@_) {
s/^(\s*)//s;
push(@leadin,$1);
# Change \{ to \QLEFTBRACE and \} to \QRIGHTBRACE
s/(?<!\\)\\{/\\QLEFTBRACE /sg;
s/(?<!\\)\\}/\\QRIGHTBRACE /sg;
# replace {,} in comments with \\CLEFTBRACE,\\CRIGHTBRACE
1 while s/((?<!\\)%.*)\{(.*)$/$1\\CLEFTBRACE $2/mg ;
1 while s/((?<!\\)%.*)\}(.*)$/$1\\CRIGHTBRACE $2/mg ;
s/\n(\s*?)\n((?:\s*\n)*)/\n$1\\PAR\n$2/g ;
s/(?<!\\)\\%/\\PERCENTAGE /g ; # (?<! is negative lookbehind assertion to prevent \\% from being converted
s/(?<!\\)\\\$/\\DOLLAR /g ; # (?<! is negative lookbehind assertion to prevent \\$ from being converted
s/(\\verb\*?)(\S)(.*?)\2/"${1}{". tohash(\%verbhash,"${2}${3}${2}") ."}"/esg;
s/\\begin\{(verbatim\*?)\}(.*?)\\end\{\1\}/"\\${1}{". tohash(\%verbhash,"${2}") . "}"/esg;
# Convert _n or _\cmd into \SUBSCRIPTNB{n} or \SUBSCRIPTNB{\cmd} and _{nnn} into \SUBSCRIPT{nn}
1 while s/(?<!\\)_([^{\\]|\\\w+)/\\SUBSCRIPTNB{$1}/g ;
1 while s/(?<!\\)_{($pat6)}/\\SUBSCRIPT{$1}/g ;
# Convert ^n into \SUPERSCRIPTNB{n} and ^{nnn} into \SUPERSCRIPT{nn}
1 while s/(?<!\\)\^([^{\\]|\\\w+)/\\SUPERSCRIPTNB{$1}/g ;
1 while s/(?<!\\)\^{($pat6)}/\\SUPERSCRIPT{$1}/g ;
# Convert $$ $$ into \begin{DOLLARDOLLAR} \end{DOLLARDOLLAR}
s/\$\$(.*?)\$\$/\\begin{DOLLARDOLLAR}$1\\end{DOLLARDOLLAR}/sg;
# Convert \[ \] into \begin{SQUAREBRACKET} \end{SQUAREBRACKET}
s/(?<!\\)\\\[/\\begin{SQUAREBRACKET}/sg;
s/\\\]/\\end{SQUAREBRACKET}/sg;
# Convert all picture environmentent (\begin{PICTUREENV} .. \end{PICTUREENV} \PICTUREBLOCKenv
s/\\begin{($PICTUREENV)}(.*?)\\end{\1}/\\PICTUREBLOCK$1\{$2\}/sg;
# For --block-math-markup option -convert all \begin{MATH} .. \end{MATH}
# into \MATHBLOCKMATH{...} commands, where MATH is any valid math environment
# Also convert all array environments into ARRAYBLOCK environments
if ( $mathmarkup != FINE ) {
s/\\begin{($ARRENV)}(.*?)\\end{\1}/\\ARRAYBLOCK$1\{$2\}/sg;
s/\\begin{($MATHENV|$MATHARRENV|SQUAREBRACKET)}(.*?)\\end{\1}/\\MATHBLOCK$1\{$2\}/sg;
}
# add final token " STOP"
$_ .= " STOP"
}
return(@leadin);
}
#hashstring=tohash(\%hash,$string)
# creates a hash value based on string and stores in %hash
sub tohash {
my ($hash,$string)=@_;
my (@arr,$val);
my ($sum,$i)=(0,1);
my ($hstr);
@arr=unpack('c*',$string);
foreach $val (@arr) {
$sum += $i*$val;
$i++;
}
$hstr= "$sum";
if (defined($hash->{$hstr}) && $string ne $hash->{$hstr}) {
warn "Repeated hash value for verbatim mode in spite of different content.";
$hstr="-$hstr";
}
$hash->{$hstr}=$string;
return($hstr);
}
#string=fromhash(\%hash,$fromstring)
# restores string value stored in hash
#string=fromhash(\%hash,$fromstring,$prependstring)
# additionally begins each line with prependstring
sub fromhash {
my ($hash,$hstr)=($_[0],$_[1]);
my $retstr=$hash->{$hstr};
if ( $#_ >= 2) {
$retstr =~ s/^/$_[2]/mg;
}
return $retstr;
}
# postprocess($string, ..)
# carry out the following post-processing steps for all arguments:
# * Remove STOP token from the end
# * Replace \RIGHTBRACE by }
# * change citation commands within comments to protect from processing (using marker CITEDIF)
# 1. Check all deleted blocks:
# a.where a deleted block contains a matching \begin and
# \end environment (these will be disabled by a %DIFDELCMD statements), for selected environments enable
# these commands again (such that for example displayed math in a deleted equation
# is properly within math mode. For math mode environments replace numbered equation
# environments with their display only variety (so that equation numbers in new file and
# diff file are identical). Where the correct type of math environment cannot be determined
# use a place holder MATHMODE
# b.where one of the commands matching $COUNTERCMD is used as a DIFAUXCMD, add a statement
# subtracting one from the respective counter to keep numbering consistent with new file
# Replace all MATHMODE environment commands by the correct environment to achieve matching
# pairs
# c. Convert MATHBLOCKmath commands to their uncounted numbers (e.g. convert equation -> displaymath
# (environments defined in $MATHENV will be replaced by $MATHREPL, and environments in $MATHARRENV
# will be replaced by $MATHARRREPL
# d. If in-line math mode contains array environment, enclose the whole environment in \mbox'es
# d. place \cite commands in mbox'es (for UNDERLINE style)
#
# For added blocks:
# c. If in-line math mode contains array environment, enclose the whole environment in \mbox'es
# d. place \cite commands in mbox'es (for UNDERLINE style)
#
# 2. If --block-math-markup option set: Convert \MATHBLOCKmath{..} commands back to environments
#
# Convert all PICTUREblock{..} commands back to the appropriate environments
# 3. Convert DIFadd, DIFdel, DIFFaddbegin , ... into FL varieties
# within floats (currently recognised float environments: plate,table,figure
# plus starred varieties).
# 4. Remove empty %DIFDELCMD < lines
# 4. Convert \begin{SQUAREBRACKET} \end{SQUAREBRACKET} into \[ \]
# Convert \begin{DOLLARDOLLAR} \end{DOLLARDOLLAR} into $$ $$
# 5. Convert \SUPERSCRIPTNB{n} into ^n and \SUPERSCRIPT{nn} into ^{nnn}
# 6. Convert \SUBSCRIPTNB{n} into _n and \SUBCRIPT{nn} into _{nnn}
# 7. Expand hashes of verb and verbatim environments
# 8. Convert '\PERCENTAGE ' back into '\%' and '\DOLLAR ' into '\$'
# 9.. remove all \PAR tokens
# 10. package specific processing: endfloat: make sure \begin{figure} and \end{figure} are always
# on a line by themselves, similarly for table environment
# 4, undo renaming of the \begin, \end,{,} in comments
# Change \QLEFTBRACE, \QRIGHTBRACE to \{,\}
#
# Note have to manually synchronize substitution commands below and
# DIF.. command names in the header
sub postprocess {
my ($begin,$len,$cnt,$float,$delblock,$addblock);
# second level blocks
my ($begin2,$cnt2,$len2,$eqarrayblock,$mathblock);
for (@_) {
# change $'s in comments to something harmless
1 while s/(%.*)\$/$1DOLLARDIF/mg ;
# Remove final STOP token
s/ STOP$//;
# Replace \RIGHTBRACE by }
s/\\RIGHTBRACE/}/g;
# change citation commands within comments to protect from processing
if ($CITECMD){
1 while s/(%.*)\\($CITECMD)/$1\\CITEDIF$2/m ;
}
# Check all deleted blocks: where a deleted block contains a matching \begin and
# \end environment (these will be disabled by a %DIFDELCMD statements), enable
# these commands again (such that for example displayed math in a deleted equation
# is properly within math mode. For math mode environments replace numbered equation
# environments with their display only variety (so that equation numbers in new file and
# diff file are identical
while ( m/\\DIFdelbegin.*?\\DIFdelend/sg ) {
$cnt=0;
$len=length($&);
$begin=pos($_) - $len;
$delblock=$&;
### (.*?[^\n]?)\n? construct is necessary to avoid empty lines in math mode, which result in
### an error
# displayed math environments
if ($mathmarkup == FINE ) {
$delblock=~ s/(\%DIFDELCMD < \s*\\begin\{((?:$MATHENV)|SQUAREBRACKET)\}.*?(?:$DELCMDCLOSE|\n))(.*?[^\n]?)\n?(\%DIFDELCMD < \s*\\end\{\2\})/\\begin{$MATHREPL}$AUXCMD\n$1$3\n\\end{$MATHREPL}$AUXCMD\n$4/sg;
# also transform the opposite pair \end{displaymath} .. \begin{displaymath} but we have to be careful not to interfere with the results of the transformation in the line directly above
### pre-0.42 obsolete version which did not work on eqnarray test $delblock=~ s/(?<!${AUXCMD}\n)(\%DIFDELCMD < \s*\\end\{($MATHENV)\}\s*?\n)(.*?[^\n]?)\n?(?<!${AUXCMD}\n)(\%DIFDELCMD < \s*\\begin\{\2\})/$1\\end{$MATHREPL}$AUXCMD\n$3\n\\begin{$MATHREPL}$AUXCMD\n$4/sg;
###0.5: $delblock=~ s/(?<!${AUXCMD}\n)(\%DIFDELCMD < \s*\\end\{((?:$MATHENV)|SQUAREBRACKET)\}\s*?(?:$DELCMDCLOSE|\n))(.*?[^\n]?)\n?(?<!${AUXCMD}\n)(\%DIFDELCMD < \s*\\begin\{\2\})/\\end{MATHMODE}$AUXCMD\n$1$3\n\\begin{MATHMODE}$AUXCMD\n$4/sg;
$delblock=~ s/(?<!${AUXCMD}\n)(\%DIFDELCMD < \s*\\end\{((?:$MATHENV)|SQUAREBRACKET)\}.*?(?:$DELCMDCLOSE|\n))(.*?[^\n]?)\n?(?<!${AUXCMD}\n)(\%DIFDELCMD < \s*\\begin\{\2\})/\\end{MATHMODE}$AUXCMD\n$1$3\n\\begin{MATHMODE}$AUXCMD\n$4/sg;
# now look for unpaired %DIFDELCMD < \begin{MATHENV}; if found add \begin{$MATHREPL} and insert \end{$MATHREPL}
# just before end of block; again we use look-behind assertion to avoid matching constructions which have already been converted
if ($delblock=~ s/(?<!${AUXCMD}\n)(\%DIFDELCMD < \s*\\begin\{((?:$MATHENV)|SQUAREBRACKET)\}\s*?(?:$DELCMDCLOSE|\n))/$1\\begin{$MATHREPL}$AUXCMD\n/sg ) {
$delblock =~ s/(\\DIFdelend$)/\\end{$MATHREPL}$AUXCMD\n$1/s ;
}
# now look for unpaired %DIFDELCMD < \end{MATHENV}; if found add \end{MATHMODE} and insert \begin{MATHMODE}
# just before end of block; again we use look-behind assertion to avoid matching constructions which have already been converted
if ($delblock=~ s/(?<!${AUXCMD}\n)(\%DIFDELCMD < \s*\\end\{((?:$MATHENV)|SQUAREBRACKET)\}\s*?(?:$DELCMDCLOSE|\n))/$1\\end{MATHMODE}$AUXCMD\n/sg ) {
$delblock =~ s/(\\DIFdelend$)/\\begin{MATHMODE}$AUXCMD\n$1/s ;
}
### pre-0.42 # same as above for special case \[.\] (latex abbreviation for displaymath)
### pre-0.42 $delblock=~ s/(\%DIFDELCMD < \s*\\\[\s*?\n())(.*?[^\n]?)\n?(\%DIFDELCMD < \s*\\\])/$1\\\[$AUXCMD\n$3\n\\\]$AUXCMD\n$4/sg;
### pre-0.42 $delblock=~ s/(?<!${AUXCMD}\n)(\%DIFDELCMD < \s*\\\]\s*?\n())(.*?[^\n]?)\n?(?<!${AUXCMD}\n)(\%DIFDELCMD < \s*\\\[)/$1\\\]$AUXCMD\n$3\n\\\[$AUXCMD\n$4/sg;
# equation array environment
###pre-0.3 $delblock=~ s/(\%DIFDELCMD < \s*\\begin\{($MATHARRENV)\}\s*?\n)(.*?)(\%DIFDELCMD < \s*\\end\{\2\})/$1\\begin{$MATHARRREPL}$AUXCMD\n$3\n\\end{$MATHARRREPL}$AUXCMD\n$4/sg;
###0.5 $delblock=~ s/(\%DIFDELCMD < \s*\\begin\{($MATHARRENV)\}\s*?(?:$DELCMDCLOSE|\n))(.*?[^\n]?)\n?(\%DIFDELCMD < \s*\\end\{\2\})/\\begin{$MATHARRREPL}$AUXCMD\n$1$3\n\\end{$MATHARRREPL}$AUXCMD\n$4/sg;
$delblock=~ s/(\%DIFDELCMD < \s*\\begin\{($MATHARRENV)\}.*?(?:$DELCMDCLOSE|\n))(.*?[^\n]?)\n?(\%DIFDELCMD < \s*\\end\{\2\})/\\begin{$MATHARRREPL}$AUXCMD\n$1$3\n\\end{$MATHARRREPL}$AUXCMD\n$4/sg;
### pre-0.42 obsolete version which did not work on eqnarray test $delblock=~ s/(?<!${AUXCMD}\n)(\%DIFDELCMD < \s*\\end\{($MATHARRENV)\}\s*?\n)(.*?[^\n]?)\n?(?<!${AUXCMD}\n)(\%DIFDELCMD < \s*\\begin\{\2\})/$1\\end{$MATHARRREPL}$AUXCMD\n$3\n\\begin{$MATHARRREPL}$AUXCMD\n$4/sg;
$delblock=~ s/(?<!${AUXCMD}\n)(\%DIFDELCMD < \s*\\end\{($MATHARRENV)\}\s*?(?:$DELCMDCLOSE|\n))(.*?[^\n]?)\n?(?<!${AUXCMD}\n)(\%DIFDELCMD < \s*\\begin\{\2\})/\\end{MATHMODE}$AUXCMD\n$1$3\n\\begin{MATHMODE}$AUXCMD\n$4/sg;
# now look for unpaired %DIFDELCMD < \begin{MATHARRENV}; if found add \begin{$MATHARRREPL} and insert \end{$MATHARRREPL}
# just before end of block; again we use look-behind assertion to avoid matching constructions which have already been converted
if ($delblock=~ s/(?<!${AUXCMD}\n)(\%DIFDELCMD < \s*\\begin\{($MATHARRENV)\}\s*?(?:$DELCMDCLOSE|\n))/$1\\begin{$MATHARRREPL}$AUXCMD\n/sg ) {
$delblock =~ s/(\\DIFdelend$)/\\end{$MATHARRREPL}$AUXCMD\n$1/s ;
}
# now look for unpaired %DIFDELCMD < \end{MATHENV}; if found add \end{MATHMODE} and insert \begin{MATHMODE}
# just before end of block; again we use look-behind assertion to avoid matching constructions which have already been converted
if ($delblock=~ s/(?<!${AUXCMD}\n)(\%DIFDELCMD < \s*\\end\{($MATHARRENV)\}\s*?(?:$DELCMDCLOSE|\n))/$1\\end{MATHMODE}$AUXCMD\n/sg ) {
$delblock =~ s/(\\DIFdelend$)/\\begin{MATHMODE}$AUXCMD\n$1/s ;
}
# parse $delblock for deleted and reinstated eqnarray* environments - within those reinstate \\ and & commands
while ( $delblock =~ m/\\begin\Q{$MATHARRREPL}$AUXCMD\E\n.*?\n\\end\Q{$MATHARRREPL}$AUXCMD\E\n/sg ) {
$cnt2=0;
$len2=length($&);
$begin2=pos($delblock) - $len2;
$eqarrayblock=$&;
# reinstate deleted & and \\ commands
$eqarrayblock=~ s/(\%DIFDELCMD < \s*(\&|\\\\)\s*?(?:$DELCMDCLOSE|\n))/$1$2$AUXCMD\n/sg ;
substr($delblock,$begin2,$len2)=$eqarrayblock;
pos($delblock) = $begin2 + length($eqarrayblock);
}
} elsif ( $mathmarkup == COARSE || $mathmarkup == WHOLE ) {
# Convert MATHBLOCKmath commands to their uncounted numbers (e.g. convert equation -> displaymath
# (environments defined in $MATHENV will be replaced by $MATHREPL, and environments in $MATHARRENV
# will be replaced by $MATHARRREPL
$delblock=~ s/\\MATHBLOCK($MATHENV)\{($pat6)\}/\\MATHBLOCK$MATHREPL\{$2\}/sg;
$delblock=~ s/\\MATHBLOCK($MATHARRENV)\{($pat6)\}/\\MATHBLOCK$MATHARRREPL\{$2\}/sg;
}
# b.where one of the commands matching $COUNTERCMD is used as a DIFAUXCMD, add a statement
# subtracting one from the respective counter to keep numbering consistent with new file
$delblock=~ s/\\($COUNTERCMD)((?:${extraspace}\[$brat0\]${extraspace}|${extraspace}\{$pat6\})*\s*${AUXCMD}\n)/\\$1$2\\addtocounter{$1}{-1}${AUXCMD}\n/sg ;
# c. If in-line math mode contains array environment, enclose the whole environment in \mbox'es
while ( $delblock =~ m/($math)(\s*)/sg ) {
$cnt2=0;
$len2=length($&);
$begin2=pos($delblock) - $len2;
$mathblock="%\n\\mbox{$AUXCMD\n$1\n}$AUXCMD\n";
next unless $mathblock =~ m/\{$ARRENV\}/ ;
substr($delblock,$begin2,$len2)=$mathblock;
pos($delblock) = $begin2 + length($mathblock);
}
if ($CITE2CMD) {
$delblock=~s/($DELCMDOPEN\s*\\($CITE2CMD)(.*)$DELCMDCLOSE)/
# Replacement code
{my ($aux,$all);
$aux=$all=$1;
$aux=~s#\n?($DELCMDOPEN|$DELCMDCLOSE)##g;
$all."$aux$AUXCMD\n";}/sge;
}
# or protect \cite commands with \mbox
if ($CITECMD) {
$delblock=~s/(\\($CITECMD)${extraspace}(?:<$abrat0>${extraspace})?(?:\[$brat0\]${extraspace}){0,2}\{$pat6\})(\s*)/\\mbox{$AUXCMD\n$1\n}$AUXCMD\n/msg ;
}
# if MBOXINLINEMATH is set, protect inlined math environments with an extra mbox
if ( $MBOXINLINEMATH ) {
# note additional \newline after command is omitted from output if right at the end of deleted block (otherwise a spurious empty line is generated)
$delblock=~s/($math)(?:[\s\n]*)?/\\mbox{$AUXCMD\n$1\n}$AUXCMD\n/sg;
}
# splice in modified delblock
substr($_,$begin,$len)=$delblock;
pos = $begin + length($delblock);
}
# make the array modification in added blocks
while ( m/\\DIFaddbegin.*?\\DIFaddend/sg ) {
$cnt=0;
$len=length($&);
$begin=pos($_) - $len;
$addblock=$&;
while ( $addblock =~ m/($math)(\s*)/sg ) {
$cnt2=0;
$len2=length($&);
$begin2=pos($addblock) - $len2;
$mathblock="%\n\\mbox{$AUXCMD\n$1\n}$AUXCMD\n";
next unless $mathblock =~ m/\{$ARRENV\}/ ;
substr($addblock,$begin2,$len2)=$mathblock;
pos($addblock) = $begin2 + length($mathblock);
}
if ($CITECMD) {
my $addblockbefore=$addblock;
#(?:mask)?(?:full|short|no)?cite(?:A|author|year|meta)(?:NP)?$/
###my $CITECMD; $CITECMD="cite(?:A)$";
$addblock=~ s/(\\($CITECMD)${extraspace}(?:<$abrat0>${extraspace})?(?:\[$brat0\]${extraspace}){0,2}\{$pat2\})(\s*)/\\mbox{$AUXCMD\n$1\n}$AUXCMD\n/msg ;
print STDERR "DEBUG: CITECMD $CITECMD\nDEBUG: addblock before:|$addblockbefore|\n" if $debug;
print STDERR "DEBUG: addblock after: |$addblock|\n" if $debug;
}
# if MBOXINLINEMATH is set, protect inlined math environments with an extra mbox
if ( $MBOXINLINEMATH ) {
##$addblock=~s/($math)/\\mbox{$AUXCMD\n$1\n}$AUXCMD\n/sg;
$addblock=~s/($math)(?:[\s\n]*)?/\\mbox{$AUXCMD\n$1\n}$AUXCMD\n/sg;
}
# splice in modified addblock
substr($_,$begin,$len)=$addblock;
pos = $begin + length($addblock);
}
# Replace MATHMODE environments from step 1a above by the correct Math environment
# The next line is complicated. The negative look-ahead insertion makes sure that no \end{$MATHENV} (or other mathematical
# environments) are between the \begin{$MATHENV} and \end{MATHMODE} commands. This is necessary as the minimal matching
# is not globally minimal but only 'locally' (matching is beginning from the left side of the string)
if ( $mathmarkup == FINE ) {
1 while s/\\begin{((?:$MATHENV)|(?:$MATHARRENV)|SQUAREBRACKET)}((?:.(?!(?:\\end{(?:(?:$MATHENV)|(?:$MATHARRENV)|SQUAREBRACKET)}|\\begin{MATHMODE})))*?)\\end{MATHMODE}/\\begin{$1}$2\\end{$1}/s;
1 while s/\\begin{MATHMODE}((?:.(?!\\end{MATHMODE}))*?)\\end{((?:$MATHENV)|(?:$MATHARRENV)|SQUAREBRACKET)}/\\begin{$2}$1\\end{$2}/s;
# convert remaining \begin{MATHMODE} \end{MATHMODE} (and not containing & or \\ )into MATHREPL environments
s/\\begin{MATHMODE}((?:(.(?!(?<!\\)\&|\\\\))*)?)\\end{MATHMODE}/\\begin{$MATHREPL}$1\\end{$MATHREPL}/sg;
# others into MATHARRREPL
s/\\begin{MATHMODE}(.*?)\\end{MATHMODE}/\\begin{$MATHARRREPL}$1\\end{$MATHARRREPL}/sg;
# now look for AUXCMD math-mode pairs which have only comments (or empty lines between them), and remove the added commands
s/\\begin{((?:$MATHENV)|(?:$MATHARRENV)|SQUAREBRACKET)}$AUXCMD\n((?:\s*%.[^\n]*\n)*)\\end{\1}$AUXCMD\n/$2/sg;
} else {
# math modes OFF,WHOLE,COARSE: Convert \MATHBLOCKmath{..} commands back to environments
s/\\MATHBLOCK($MATHENV|$MATHARRENV|SQUAREBRACKET)\{($pat6)\}/\\begin{$1}$2\\end{$1}/sg;
# convert ARRAYBLOCK.. commands back to environments
s/\\ARRAYBLOCK($ARRENV)\{($pat6)\}/\\begin{$1}$2\\end{$1}/sg;
}
# Convert all PICTUREblock{..} commands back to the appropriate environments
s/\\PICTUREBLOCK($PICTUREENV)\{($pat6)\}/\\begin{$1}$2\\end{$1}/sg;
#0.5: # Remove all mark up within picture environments
# while ( m/\\begin\{($PICTUREENV)\}.*?\\end\{\1\}/sg ) {
# $cnt=0;
# $len=length($&);
# $begin=pos($_) - $len;
# $float=$&;
# $float =~ s/\\DIFaddbegin //g;
# $float =~ s/\\DIFaddend //g;
# $float =~ s/\\DIFadd\{($pat6)\}/$1/g;
# $float =~ s/\\DIFdelbegin //g;
# $float =~ s/\\DIFdelend //g;
# $float =~ s/\\DIFdel\{($pat6)\}//g;
# $float =~ s/$DELCMDOPEN.*//g;
# substr($_,$begin,$len)=$float;
# pos = $begin + length($float);
# }
# Convert DIFadd, DIFdel, DIFFaddbegin , ... into varieties
# within floats (currently recognised float environments: plate,table,figure
# plus starred varieties).
while ( m/\\begin\{($FLOATENV)\}.*?\\end\{\1\}/sg ) {
$cnt=0;
$len=length($&);
$begin=pos($_) - $len;
$float=$&;
$float =~ s/\\DIFaddbegin /\\DIFaddbeginFL /g;
$float =~ s/\\DIFaddend /\\DIFaddendFL /g;
$float =~ s/\\DIFadd\{/\\DIFaddFL{/g;
$float =~ s/\\DIFdelbegin /\\DIFdelbeginFL /g;
$float =~ s/\\DIFdelend /\\DIFdelendFL /g;
$float =~ s/\\DIFdel\{/\\DIFdelFL{/g;
substr($_,$begin,$len)=$float;
pos = $begin + length($float);
}
### former location of undo renaming of \begin and \end in comments
# remove empty DIFCMD < lines
s/^\Q${DELCMDOPEN}\E\n//msg;
# Expand hashes of verb and verbatim environments (note negative look behind assertion to not leak out of DIFDELCMD comments
s/(\\verb\*?)\{([-\d]*?)\}/"${1}". fromhash(\%verbhash,$2)/esg;
s/${DELCMDOPEN}\\(verbatim\*?)\{([-\d]*?)\}/"${DELCMDOPEN}\\begin{${1}}".fromhash(\%verbhash,$2,$DELCMDOPEN)."${DELCMDOPEN}\\end{${1}}"/esg;
s/\\(verbatim\*?)\{([-\d]*?)\}/"\\begin{${1}}".fromhash(\%verbhash,$2)."\\end{${1}}"/esg;
# Convert '\PERCENTAGE ' back into '\%' (the final question mark catches a special situation where due to a latter pre-processing step the ' ' becomes separated
s/\\PERCENTAGE ?/\\%/g;
# Convert '\DOLLAR ' back into '\$'
s/\\DOLLAR /\\\$/g;
# remove all \PAR tokens (taking care to properly keep commented out PAR's
# from introducing uncommented newlines - next line)
s/(%DIF < )([^\n]*?)\\PAR\n/$1$2\n$1\n/sg;
# convert PAR commands which are on a line by themselves
s/\n(\s*?)\\PAR\n/\n\n/sg;
# convert remaining PAR commands (which are preceded by non-white space characters, usually "}" ($ADDCLOSE)
s/\\PAR\n/\n\n/sg;
# package specific processing:
if ( defined($packages{"endfloat"})) {
#endfloat: make sure \begin{figure} and \end{figure} are always
# on a line by themselves, similarly for table environment
print STDERR "endfloat package detected.\n" if $verbose ;
# eliminate whitespace before and after
s/^(\s*)(\\(?:begin|end)\{(?:figure|table)\})(\s*)$/$2/mg;
# split lines with remaining characters before float enviroment conmmand
s/^(.+)(\\(?:begin|end)\{(?:figure|table)\})/$1\n$2/mg;
# split lines with remaining characters after float enviroment conmmand
s/(\\(?:begin|end)\{(?:figure|table)\})(.+)$/$1\n$2/mg;
}
# undo renaming of the \begin and \end,{,} and dollars in comments
1 while s/(%.*)DOLLARDIF/$1\$/mg ;
# undo renaming of the \cite.. commands in comments
if ( $CITECMD ) {
1 while s/(%.*)\\CITEDIF($CITECMD)/$1\\$2/mg ;
}
# Convert \begin{SQUAREBRACKET} \end{SQUAREBRACKET} into \[ \]
s/\\end{SQUAREBRACKET}/\\\]/sg;
s/\\begin{SQUAREBRACKET}/\\\[/sg;
# 4. Convert \begin{DOLLARDOLLAR} \end{DOLLARDOLLAR} into $$ $$
s/\\begin\{DOLLARDOLLAR\}(.*?)\\end\{DOLLARDOLLAR\}/\$\$$1\$\$/sg;
# 5. Convert \SUPERSCRIPTNB{n} into ^n and \SUPERSCRIPT{nn} into ^{nnn}
1 while s/\\SUPERSCRIPT{($pat6)}/^{$1}/g ;
1 while s/\\SUPERSCRIPTNB{($pat0)}/^$1/g ;
# Convert \SUBSCRIPNB{n} into _n and \SUBCRIPT{nn} into _{nnn}
1 while s/\\SUBSCRIPT{($pat6)}/_{$1}/g ;
1 while s/\\SUBSCRIPTNB{($pat0)}/_$1/g ;
1 while s/(%.*)\\CRIGHTBRACE (.*)$/$1\}$2/mg ;
1 while s/(%.*)\\CLEFTBRACE (.*)$/$1\{$2/mg ;
# Change \QLEFTBRACE, \QRIGHTBRACE to \{,\}
s/\\QLEFTBRACE /\\{/sg;
s/\\QRIGHTBRACE /\\}/sg;
return;
}
}
# @auxlines=preprocess_preamble($oldpreamble,$newpreamble);
# pre-process preamble by looking for commands used in \maketitle (title, author, date etc commands)
# if found then use a bodydiff to mark up content, and replace the corresponding commands
# in both preambles by marked up version to 'fool' the linediff (such that only body is marked
# up.
# A special case are e.g. author commands being added (or removed)
# 1. If commands are added, then the entire content is marked up as new, but also the lines are marked as new in the linediff
# 2. If commands are removed, then the linediff will mark the line as deleted. The program returns
# with $auxlines a text to be appended at the end of the preamble, which shows the respective fields as deleted
sub preprocess_preamble {
my ($oldpreambleref,$newpreambleref)=(\$_[0],\$_[1]) ;
my @auxlines=();
# Remember to use $$oldpreambleref to refer to oldpreamble
my ($titlecmd,$titlecmdpat);
my (@oldtitlecommands,@newtitlecommands );
my %oldhash = ();
my %newhash = ();
my ($line,$cmd,$optarg,$arg,$optargnew,$optargold,$optargdiff,$argold,$argnew,$argdiff,$auxline);
# resuse context2cmdlist to define these commands to look out for in preamble
$titlecmd = "(?:".join("|",@CONTEXT2CMDLIST).")";
# as context2cmdlist is stored as regex, e.g. ((?-xism:^title$), we need to remove ^- fo
# resue in a more complex regex
$titlecmd =~ s/[\$\^]//g;
# make sure to not match on comment lines:
$titlecmdpat=qr/^(?:[^%\n]|\\%)*(\\($titlecmd)$extraspace(?:\[($brat0)\])?(?:\{($pat6)\}))/ms;
@oldtitlecommands= ( $$oldpreambleref =~ m/$titlecmdpat/g );
@newtitlecommands= ( $$newpreambleref =~ m/$titlecmdpat/g );
while ( @oldtitlecommands ) {
$line=shift @oldtitlecommands;
$cmd=shift @oldtitlecommands;
$optarg=shift @oldtitlecommands;
$arg=shift @oldtitlecommands;
if ( defined($oldhash{$cmd})) {
warn "$cmd is used twice in preamble of old file. Reverting to pure line diff mode for preamble.\n";
return;
}
$oldhash{$cmd}=[ $line, $optarg, $arg ];
}
while ( @newtitlecommands ) {
$line=shift @newtitlecommands;
$cmd=shift @newtitlecommands;
$optarg=shift @newtitlecommands;
$arg=shift @newtitlecommands;
if ( defined($newhash{$cmd})) {
warn "$cmd is used twice in preamble of new file. Reverting to pure line diff mode for preamble.\n";
return;
}
$newhash{$cmd}=[ $line, $optarg, $arg ];
}
foreach $cmd ( keys %newhash ) {
if ( defined($newhash{$cmd}->[1])) {
$optargnew=$newhash{$cmd}->[1];
} else {
$optargnew="";
}
if ( defined($oldhash{$cmd}->[1])) {
$optargold=$oldhash{$cmd}->[1];
} else {
$optargold="";
}
if ( defined($oldhash{$cmd}) ) {
$argold=$oldhash{$cmd}->[2];
} else {
$argold="";
}
$argnew=$newhash{$cmd}->[2];
$argdiff="{" . join("",bodydiff($argold,$argnew)) ."}";
if ( length $optargnew ) {
$optargdiff="[".join("",bodydiff($optargold,$optargnew))."]" ;
$optargdiff =~ s/\\DIFaddbegin /\\DIFaddbeginFL /g;
$optargdiff =~ s/\\DIFaddend /\\DIFaddendFL /g;
$optargdiff =~ s/\\DIFadd\{/\\DIFaddFL{/g;
$optargdiff =~ s/\\DIFdelbegin /\\DIFdelbeginFL /g;
$optargdiff =~ s/\\DIFdelend /\\DIFdelendFL /g;
$optargdiff =~ s/\\DIFdel\{/\\DIFdelFL{/g;
} else {
$optargdiff="";
}
### print STDERR "DEBUG s/\\Q$newhash{$cmd}->[0]\\E/\\$cmd$optargdiff$argdiff/s\n";
# Note: \Q and \E force literal interpretation of what it between them but allow
# variable interpolation, such that e.g. \title matches just that and not TAB-itle
$$newpreambleref=~s/\Q$newhash{$cmd}->[0]\E/\\$cmd$optargdiff$argdiff/s;
# replace this in old preamble if necessary
if ( defined($oldhash{$cmd}->[0])) {
$$oldpreambleref=~s/\Q$oldhash{$cmd}->[0]\E/\\$cmd$optargdiff$argdiff/s ;
}
### print STDERR "DEBUG NEW PRE ".$$newpreambleref."\n";
}
foreach $cmd ( keys %oldhash ) {
# if this has already been dealt with above can just skip
next if defined($newhash{$cmd}) ;
if ( defined($oldhash{$cmd}->[1])) {
$optargold=$oldhash{$cmd}->[1];
$optargdiff="[".join("",bodydiff($optargold,""))."]" ;
$optargdiff =~ s/\\DIFdelbegin /\\DIFdelbeginFL /g;
$optargdiff =~ s/\\DIFdelend /\\DIFdelendFL /g;
$optargdiff =~ s/\\DIFdel\{/\\DIFdelFL{/g;
} else {
$optargdiff="";
}
$argdiff="{" . join("",bodydiff($argold,"")) ."}";
$auxline = "\\$cmd$optargdiff$argdiff";
$auxline =~s/$/$AUXCMD/sg;
push @auxlines,$auxline;
}
# add auxcmd comment to highlight added lines
return(@auxlines);
}
# @diffs=linediff(\@seq1, \@seq2)
# mark up lines like this
#%DIF mm-mmdnn
#%< old deleted line(s)
#%DIF -------
#%DIF mmann-nn
#new appended line %<
#%DIF -------
# Future extension: mark change explicitly
# Assumes: traverse_sequence traverses deletions before insertions in changed sequences
# all line numbers relative to line 0 (first line of real file)
sub linediff {
my $seq1 = shift ;
my $seq2 = shift ;
my $block = [];
my $retseq = [];
my @begin=('','',''); # dummy initialisation
my $instring ;
my $discard = sub { @begin=('d',$_[0],$_[1]) unless scalar @$block ;
push(@$block, "%DIF < " . $seq1->[$_[0]]) };
my $add = sub { if (! scalar @$block) {
@begin=('a',$_[0],$_[1]) ;}
elsif ( $begin[0] eq 'd' ) {
$begin[0]='c'; $begin[2]=$_[1];
push(@$block, "%DIF -------") }
push(@$block, $seq2->[$_[1]] . " %DIF > " ) };
my $match = sub { if ( scalar @$block ) {
if ( $begin[0] eq 'd' && $begin[1]!=$_[0]-1) {
$instring = sprintf "%%DIF %d-%dd%d",$begin[1],$_[0]-1,$begin[2]; }
elsif ( $begin[0] eq 'a' && $begin[2]!=$_[1]-1) {
$instring = sprintf "%%DIF %da%d-%d",$begin[1],$begin[2],$_[1]-1; }
elsif ( $begin[0] eq 'c' ) {
$instring = sprintf "%%DIF %sc%s",
($begin[1]==$_[0]-1) ? "$begin[1]" : $begin[1]."-".($_[0]-1) ,
($begin[2]==$_[1]-1) ? "$begin[2]" : $begin[2]."-".($_[1]-1) ; }
else {
$instring = sprintf "%%DIF %d%s%d",$begin[1],$begin[0],$begin[2]; }
push @$retseq, $instring,@$block, "%DIF -------" ;
$block = [];
}
push @$retseq, $seq2->[$_[1]]
};
# key function: remove multiple spaces (such that insertion or deletion of redundant white space is not reported)
my $keyfunc = sub { join(" ",split(" ",shift())) };
traverse_sequences($seq1,$seq2, { MATCH=>$match, DISCARD_A=>$discard, DISCARD_B=>$add }, $keyfunc );
push @$retseq, @$block if scalar @$block;
return wantarray ? @$retseq : $retseq ;
}
# init_regex_arr_data(\@array,"TOKEN INIT")
# scans DATA file handel for line "%% TOKEN INIT" line
# then appends each line not beginning with % into array (as a quoted regex)
sub init_regex_arr_data {
my ($arr,$token)=@_;
my ($copy);
while (<DATA>) {
if ( m/^%%BEGIN $token\s*$/ ) {
$copy=1; }
elsif ( m/^%%END $token\s*/ ) {
last; }
chomp;
push (@$arr,qr/^$_$/) if ( $copy && !/^%/ ) ;
}
seek DATA,0,0; # rewind DATA handle to file begin
}
# init_regex_arr_ext(\@array,$arg)
# fills array with regular expressions.
# if arg is a file name, then read in list of regular expressions from that file
# (one expression per line)
# Otherwise treat arg as a comma separated list of regular expressions
sub init_regex_arr_ext {
my ($arr,$arg)=@_;
my $regex;
if ( -f $ arg ) {
open(FILE,"$arg") or die ("Couldn't open $arg: $!");
while (<FILE>) {
chomp;
next if /^\s*#/ || /^\s*%/ || /^\s*$/ ;
push (@$arr,qr/^$_$/);
}
close(FILE);
}
else {
# assume it is a comma-separated list of reg-ex
foreach $regex (split(qr/(?<!\\),/,$arg)) {
$regex =~ s/\\,/,/g;
push (@$arr,qr/^$regex$/);
}
}
}
#exetime() returns time since last execution of this command
#exetime(1) resets this time
my $lasttime=-1; # global variable for persistence
sub exetime {
my $reset=0;
my $retval;
if ((scalar @_) >=1) {
$reset=shift;
}
if ($reset) {
$lasttime=times();
}
else {
$retval=times()-$lasttime;
$lasttime=$lasttime+$retval;
return($retval);
}
}
sub usage {
die <<"EOF";
Usage: $0 [options] old.tex new.tex > diff.tex
Compares two latex files and writes tex code to stdout, which has the same
format as new.tex but has all changes relative to old.tex marked up or commented.
--type=markupstyle
-t markupstyle Add code to preamble for selected markup style
Available styles: UNDERLINE CTRADITIONAL TRADITIONAL CFONT FONTSTRIKE INVISIBLE
CHANGEBAR CCHANGEBAR CULINECHBAR CFONTCBHBAR
[ Default: UNDERLINE ]
--subtype=markstyle
-s markstyle Add code to preamble for selected style for bracketing
commands (e.g. to mark changes in margin)
Available styles: SAFE MARGINAL DVIPSCOL COLOR LABEL
[ Default: SAFE ]
--floattype=markstyle
-f markstyle Add code to preamble for selected style which
replace standard marking and markup commands within floats
(e.g., marginal remarks cause an error within floats
so marginal marking can be disabled thus)
Available styles: FLOATSAFE IDENTICAL
[ Default: FLOATSAFE ]
--encoding=enc
-e enc Specify encoding of old.tex and new.tex. Typical encodings are
ascii, utf8, latin1, latin9. A list of available encodings can be
obtained by executing
perl -MEncode -e 'print join ("\\n",Encode->encodings( ":all" )) ;'
[Default encoding is utf8 unless the first few lines of the preamble contain
an invocation "\\usepackage[..]{inputenc} in which case the
encoding chosen by this command is asssumed. Note that ASCII (standard
latex) is a subset of utf8]
--preamble=file
-p file Insert file at end of preamble instead of auto-generating
preamble. The preamble must define the following commands
\\DIFaddbegin,\\DIFaddend,\\DIFadd{..},
\\DIFdelbegin,\\DIFdelend,\\DIFdel{..},
and varieties for use within floats
\\DIFaddbeginFL,\\DIFaddendFL,\\DIFaddFL{..},
\\DIFdelbeginFL,\\DIFdelendFL,\\DIFdelFL{..}
(If this option is set -t, -s, and -f options
are ignored.)
--exclude-safecmd=exclude-file
--exclude-safecmd="cmd1,cmd2,..."
-A exclude-file
--replace-safecmd=replace-file
--append-safecmd=append-file
--append-safecmd="cmd1,cmd2,..."
-a append-file Exclude from, replace or append to the list of regex
matching commands which are safe to use within the
scope of a \\DIFadd or \\DIFdel command. The file must contain
one Perl-RegEx per line (Comment lines beginning with # or % are
ignored). A literal comma within the comma-separated list must be
escaped thus "\\,", Note that the RegEx needs to match the whole of
the token, i.e., /^regex\$/ is implied and that the initial
"\\" of the command is not included. The --exclude-safecmd
and --append-safecmd options can be combined with the --replace-safecmd
option and can be used repeatedly to add cumulatively to the lists.
--exclude-textcmd=exclude-file
--exclude-textcmd="cmd1,cmd2,..."
-X exclude-file
--replace-textcmd=replace-file
--append-textcmd=append-file
--append-textcmd="cmd1,cmd2,..."
-x append-file Exclude from, replace or append to the list of regex
matching commands whose last argument is text. See
entry for --exclude-safecmd directly above for further details.
--replace-context1cmd=replace-file
--append-context1cmd=append-file
--append-context1cmd="cmd1,cmd2,..."
Replace or append to the list of regex matching commands
whose last argument is text but which require a particular
context to work, e.g. \\caption will only work within a figure
or table. These commands behave like text commands, except when
they occur in a deleted section, when they are disabled, but their
argument is shown as deleted text.
--replace-context2cmd=replace-file
--append-context2cmd=append-file
--append-context2cmd="cmd1,cmd2,..."
As corresponding commands for context1. The only difference is that
context2 commands are completely disabled in deleted sections, including
their arguments.
--config var1=val1,var2=val2,...
-c var1=val1,.. Set configuration variables.
-c configfile Available variables:
MINWORDSBLOCK (integer)
FLOATENV (RegEx)
PICTUREENV (RegEx)
MATHENV (RegEx)
MATHREPL (String)
MATHARRENV (RegEx)
MATHARRREPL (String)
ARRENV (RegEx)
COUNTERCMD (RegEx)
This option can be repeated.
--packages=pkg1,pkg2,..
Tell latexdiff that .tex file is processed with the packages in list
loaded. This is normally not necessary if the .tex file includes the
preamble, as the preamble is automatically scanned for \\usepackage commands.
Use of the --packages option disables automatic scanning, so if for any
reason package specific parsing needs to be switched off, use --packages=none.
The following packages trigger special behaviour:
endfloat hyperref amsmath apacite
[ Default: scan the preamble for \\usepackage commands to determine
loaded packages.]
--show-preamble Print generated or included preamble commands to stdout.
--show-safecmd Print list of regex matching and excluding safe commands.
--show-textcmd Print list of regex matching and excluding commands with text argument.
--show-config Show values of configuration variables
--show-all Show all of the above
NB For all --show commands, no old.tex or new.tex file needs to be given, and no
differencing takes place.
Other configuration options:
--allow-spaces Allow spaces between bracketed or braced arguments to commands
[Default requires arguments to directly follow each other without
intervening spaces]
--math-markup=level Determine granularity of markup in displayed math environments:
Possible values for level are (both numerical and text labels are acceptable):
off or 0: suppress markup for math environments. Deleted equations will not
appear in diff file. This mode can be used if all the other modes
cause invalid latex code.
whole or 1: Differencing on the level of whole equations. Even trivial changes
to equations cause the whole equation to be marked changed. This
mode can be used if processing in coarse or fine mode results in
invalid latex code.
coarse or 2: Detect changes within equations marked up with a coarse
granularity; changes in equation type (e.g.displaymath to equation)
appear as a change to the complete equation. This mode is recommended
for situations where the content and order of some equations are still
being changed. [Default]
fine or 3: Detect small change in equations and mark up and fine granularity.
This mode is most suitable, if only minor changes to equations are
expected, e.g. correction of typos.
--disable-citation-markup Suppress citation markup in styles using ulem (UNDERLINE,
FONTSTRIKE, CULINECHBAR)
--enable-citation-markup Protect citation commands in changed sections with \\mbox command
[i.e. use default behaviour for ulem package for other packages]
Miscelleneous options
--label=label
-L label Sets the labels used to describe the old and new files. The first use
of this option sets the label describing the old file and the second
use of the option sets the label for the new file.
[Default: use the filename and modification dates for the label]
--no-label Suppress inclusion of old and new file names as comment in output file
--visible-label Include old and new filenames (or labels set with --label option) as
visible output
--flatten Replace \\input and \\include commands within body by the content
of the files in their argument. If \\includeonly is present in the
preamble, only those files are expanded into the document. However,
no recursion is done, i.e. \\input and \\include commands within
included sections are not expanded. The included files are assumed to
be located in the same directories as the old and new master files,
respectively, making it possible to organise files into old and new directories.
--flatten is applied recursively, so inputted files can contain further
\\input statements.
--help
-h Show this help text.
--ignore-warnings Suppress warnings about inconsistencies in length between input
and parsed strings and missing characters.
--verbose
-V Output various status information to stderr during processing.
Default is to work silently.
--version Show version number.
EOF
}
=head1 NAME
latexdiff - determine and markup differences between two latex files
=head1 SYNOPSIS
B<latexdiff> [ B<OPTIONS> ] F<old.tex> F<new.tex> > F<diff.tex>
=head1 DESCRIPTION
Briefly, I<latexdiff> is a utility program to aid in the management of
revisions of latex documents. It compares two valid latex files, here
called C<old.tex> and C<new.tex>, finds significant differences
between them (i.e., ignoring the number of white spaces and position
of line breaks), and adds special commands to highlight the
differences. Where visual highlighting is not possible, e.g. for changes
in the formatting, the differences are
nevertheless marked up in the source.
The program treats the preamble differently from the main document.
Differences between the preambles are found using line-based
differencing (similarly to the Unix diff command, but ignoring white
spaces). A comment, "S<C<%DIF E<gt>>>" is appended to each added line, i.e. a
line present in C<new.tex> but not in C<old.tex>. Discarded lines
are deactivated by prepending "S<C<%DIF E<lt>>>". Changed blocks are preceded by
comment lines giving information about line numbers in the original files. Where there are insignificant
differences, the resulting file C<diff.tex> will be similar to
C<new.tex>. At the end of the preamble, the definitions for I<latexdiff> markup commands are inserted.
In differencing the main body of the text, I<latexdiff> attempts to
satisfy the following guidelines (in order of priority):
=over 3
=item 1
If both C<old.tex> and C<new.tex> are valid LaTeX, then the resulting
C<diff.tex> should also be valid LateX. (NB If a few plain TeX commands
are used within C<old.tex> or C<new.tex> then C<diff.tex> is not
guaranteed to work but usually will).
=item 2
Significant differences are determined on the level of
individual words. All significant differences, including differences
between comments should be clearly marked in the resulting source code
C<diff.tex>.
=item 3
If a changed passage contains text or text-producing commands, then
running C<diff.tex> through LateX should produce output where added
and discarded passages are highlighted.
=item 4
Where there are insignificant differences, e.g. in the positioning of
line breaks, C<diff.tex> should follow the formatting of C<new.tex>
=back
For differencing the same algorithm as I<diff> is used but words
instead of lines are compared. An attempt is made to recognize
blocks which are completely changed such that they can be marked up as a unit.
Comments are differenced line by line
but the number of spaces within comments is ignored. Commands including
all their arguments are generally compared as one unit, i.e., no mark-up
is inserted into the arguments of commands. However, for a selected
number of commands (for example, C<\caption> and all sectioning
commands) the last argument is known to be text. This text is
split into words and differenced just as ordinary text (use options to
show and change the list of text commands, see below). As the
algorithm has no detailed knowledge of LaTeX, it assumes all pairs of
curly braces immediately following a command (i.e. a sequence of
letters beginning with a backslash) are arguments for that command.
As a restriction to condition 1 above it is thus necessary to surround
all arguments with curly braces, and to not insert
extraneous spaces. For example, write
\section{\textem{This is an emphasized section title}}
and not
\section {\textem{This is an emphasized section title}}
or
\section\textem{This is an emphasized section title}
even though all varieties are the same to LaTeX (but see
B<--allow-spaces> option which allows the second variety).
For environments whose content does not conform to standard LaTeX or
where graphical markup does not make sense all markup commands can be
removed by setting the PICTUREENV configuration variable, set by
default to C<picture> and C<DIFnomarkup> environments; see B<--config>
option). The latter environment (C<DIFnomarkup>) can be used to
protect parts of the latex file where the markup results in illegal
markup. You have to surround the offending passage in both the old and
new file by C<\begin{DIFnomarkup}> and C<\end{DIFnomarkup}>. You must
define the environment in the preambles of both old and new
documents. I prefer to define it as a null-environment,
C<\newenvironment{DIFnomarkup}{}{}>
but the choice is yours. Any markup within the environment will be
removed, and generally everything within the environment will just be
taken from the new file.
It is also possible to difference files which do not have a preamble.
In this case, the file is processed in the main document
mode, but the definitions of the markup commands are not inserted.
All markup commands inserted by I<latexdiff> begin with "C<\DIF>". Added
blocks containing words, commands or comments which are in C<new.tex>
but not in C<old.tex> are marked by C<\DIFaddbegin> and C<\DIFaddend>.
Discarded blocks are marked by C<\DIFdelbegin> and C<\DIFdelend>.
Within added blocks all text is highlighted with C<\DIFadd> like this:
C<\DIFadd{Added text block}>
Selected `safe' commands can be contained in these text blocks as well
(use options to show and change the list of safe commands, see below).
All other commands as well as braces "{" and "}" are never put within
the scope of C<\DIFadd>. Added comments are marked by prepending
"S<C<%DIF E<gt> >>".
Within deleted blocks text is highlighted with C<\DIFdel>. Deleted
comments are marked by prepending "S<C<%DIF E<lt> >>". Non-safe command
and curly braces within deleted blocks are commented out with
"S<C<%DIFDELCMD E<lt> >>".
=head1 OPTIONS
=head2 Preamble
The following options determine the visual markup style by adding the appropriate
command definitions to the preamble. See the end of this section for a description of
available styles.
=over 4
=item B<--type=markupstyle> or
B<-t markupstyle>
Add code to preamble for selected markup style. This option defines
C<\DIFadd> and C<\DIFdel> commands.
Available styles:
C<UNDERLINE CTRADITIONAL TRADITIONAL CFONT FONTSTRIKE INVISIBLE
CHANGEBAR CCHANGEBAR CULINECHBAR CFONTCBHBAR>
[ Default: C<UNDERLINE> ]
=item B<--subtype=markstyle> or
B<-s markstyle>
Add code to preamble for selected style for bracketing
commands (e.g. to mark changes in margin). This option defines
C<\DIFaddbegin>, C<\DIFaddend>, C<\DIFdelbegin> and C<\DIFdelend> commands.
Available styles: C<SAFE MARGINAL COLOR DVIPSCOL LABEL>
[ Default: C<SAFE> ]
=item B<--floattype=markstyle> or
B<-f markstyle>
Add code to preamble for selected style which
replace standard marking and markup commands within floats
(e.g., marginal remarks cause an error within floats
so marginal marking can be disabled thus). This option defines all
C<\DIF...FL> commands.
Available styles: C<FLOATSAFE TRADITIONALSAFE IDENTICAL>
[ Default: C<FLOATSAFE> ]
=item B<--encoding=enc> or
B<-e enc>
Specify encoding of old.tex and new.tex. Typical encodings are
C<ascii>, C<utf8>, C<latin1>, C<latin9>. A list of available encodings can be
obtained by executing
C<perl -MEncode -e 'print join ("\n",Encode->encodings( ":all" )) ;' >
[Default encoding is utf8 unless the first few lines of the preamble contain
an invocation C<\usepackage[..]{inputenc}> in which case the
encoding chosen by this command is asssumed. Note that ASCII (standard
latex) is a subset of utf8]
=item B<--preamble=file> or
B<-p file>
Insert file at end of preamble instead of generating
preamble. The preamble must define the following commands
C<\DIFaddbegin, \DIFaddend, \DIFadd{..},
\DIFdelbegin,\DIFdelend,\DIFdel{..},>
and varieties for use within floats
C<\DIFaddbeginFL, \DIFaddendFL, \DIFaddFL{..},
\DIFdelbeginFL, \DIFdelendFL, \DIFdelFL{..}>
(If this option is set B<-t>, B<-s>, and B<-f> options
are ignored.)
=item B<--packages=pkg1,pkg2,..>
Tell latexdiff that .tex file is processed with the packages in list
loaded. This is normally not necessary if the .tex file includes the
preamble, as the preamble is automatically scanned for C<\usepackage> commands.
Use of the B<--packages> option disables automatic scanning, so if for any
reason package specific parsing needs to be switched off, use B<--packages=none>.
The following packages trigger special behaviour:
=over 8
=item C<amsmath>
Configuration variable amsmath is set to C<align*> (Default: C<eqnarray*>)
=item C<endfloat>
Ensure that C<\begin{figure}> and C<\end{figure}> always appear by themselves on a line.
=item C<hyperref>
Change name of C<\DIFadd> and C<\DIFdel> commands to C<\DIFaddtex> and C<\DIFdeltex> and
define new C<\DIFadd> and C<\DIFdel> commands, which provide a wrapper for these commands,
using them for the text but not for the link defining command (where any markup would cause
errors).
=item C<apacite>
Redefine the commands recognised as citation commands.
=back
[ Default: scan the preamble for C<\\usepackage> commands to determine
loaded packages.]
=item B<--show-preamble>
Print generated or included preamble commands to stdout.
=back
=head2 Configuration
=over 4
=item B<--exclude-safecmd=exclude-file> or
B<-A exclude-file> or B<--exclude-safecmd="cmd1,cmd2,...">
=item B<--replace-safecmd=replace-file>
=item B<--append-safecmd=append-file> or
B<-a append-file> or B<--append-safecmd="cmd1,cmd2,...">
Exclude from, replace or append to the list of regular expressions (RegEx)
matching commands which are safe to use within the
scope of a C<\DIFadd> or C<\DIFdel> command. The file must contain
one Perl-RegEx per line (Comment lines beginning with # or % are
ignored). Note that the RegEx needs to match the whole of
the token, i.e., /^regex$/ is implied and that the initial
"\" of the command is not included.
The B<--exclude-safecmd> and B<--append-safecmd> options can be combined with the -B<--replace-safecmd>
option and can be used repeatedly to add cumulatively to the lists.
B<--exclude-safecmd>
and B<--append-safecmd> can also take a comma separated list as input. If a
comma for one of the regex is required, escape it thus "\,". In most cases it
will be necessary to protect the comma-separated list from the shell by putting
it in quotation marks.
=item B<--exclude-textcmd=exclude-file> or
B<-X exclude-file> or B<--exclude-textcmd="cmd1,cmd2,...">
=item B<--replace-textcmd=replace-file>
=item B<--append-textcmd=append-file> or
B<-x append-file> or B<--append-textcmd="cmd1,cmd2,...">
Exclude from, replace or append to the list of regular expressions
matching commands whose last argument is text. See
entry for B<--exclude-safecmd> directly above for further details.
=item B<--replace-context1cmd=replace-file>
=item B<--append-context1cmd=append-file> or
=item B<--append-context1cmd="cmd1,cmd2,...">
Replace or append to the list of regex matching commands
whose last argument is text but which require a particular
context to work, e.g. \caption will only work within a figure
or table. These commands behave like text commands, except when
they occur in a deleted section, when they are disabled, but their
argument is shown as deleted text.
=item B<--replace-context2cmd=replace-file>
=item B<--append-context2cmd=append-file> or
=item B<--append-context2cmd="cmd1,cmd2,...">
As corresponding commands for context1. The only difference is that
context2 commands are completely disabled in deleted sections, including
their arguments.
=item B<--config var1=val1,var2=val2,...> or B<-c var1=val1,..>
=item B<-c configfile>
Set configuration variables. The option can be repeated to set different
variables (as an alternative to the comma-separated list).
Available variables (see below for further explanations):
C<MINWORDSBLOCK> (integer)
C<FLOATENV> (RegEx)
C<PICTUREENV> (RegEx)
C<MATHENV> (RegEx)
C<MATHREPL> (String)
C<MATHARRENV> (RegEx)
C<MATHARRREPL> (String)
C<ARRENV> (RegEx)
C<COUNTERCMD> (RegEx)
=item B<--show-safecmd>
Print list of RegEx matching and excluding safe commands.
=item B<--show-textcmd>
Print list of RegEx matching and excluding commands with text argument.
=item B<--show-config>
Show values of configuration variables.
=item B<--show-all>
Combine all --show commands.
NB For all --show commands, no C<old.tex> or C<new.tex> file needs to be specified, and no
differencing takes place.
=back
=head2 Other configuration options:
=over 4
=item B<--allow-spaces>
Allow spaces between bracketed or braced arguments to commands. Note
that this option might have undesirable side effects (unrelated scope
might get lumpeded with preceding commands) so should only be used if the
default produces erroneous results. (Default requires arguments to
directly follow each other without intervening spaces).
=item B<--math-markup=level>
Determine granularity of markup in displayed math environments:
Possible values for level are (both numerical and text labels are acceptable):
C<off> or C<0>: suppress markup for math environments. Deleted equations will not
appear in diff file. This mode can be used if all the other modes
cause invalid latex code.
C<whole> or C<1>: Differencing on the level of whole equations. Even trivial changes
to equations cause the whole equation to be marked changed. This
mode can be used if processing in coarse or fine mode results in
invalid latex code.
C<coarse> or C<2>: Detect changes within equations marked up with a coarse
granularity; changes in equation type (e.g.displaymath to equation)
appear as a change to the complete equation. This mode is recommended
for situations where the content and order of some equations are still
being changed. [Default]
C<fine> or C<3>: Detect small change in equations and mark up at fine granularity.
This mode is most suitable, if only minor changes to equations are
expected, e.g. correction of typos.
=item B<--disable-citation-markup>
Suppress citation markup in styles using ulem (UNDERLINE,
FONTSTRIKE, CULINECHBAR)
=item B<--enable-citation-markup>
Protect citation commands in changed sections with \\mbox command [i.e. use default behaviour for ulem package for other packages]
=back
=head2 Miscellaneous
=over 4
=item B<--verbose> or B<-V>
Output various status information to stderr during processing.
Default is to work silently.
=item B<--driver=type>
Choose driver for changebar package (only relevant for styles using
changebar: CCHANGEBAR CFONTCHBAR CULINECHBAR CHANGEBAR). Possible
drivers are listed in changebar manual, e.g. pdftex,dvips,dvitops
[Default: dvips]
=item B<--ignore-warnings>
Suppress warnings about inconsistencies in length between input and
parsed strings and missing characters. These warning messages are
often related to non-standard latex or latex constructions with a
syntax unknown to C<latexdiff> but the resulting difference argument
is often fully functional anyway, particularly if the non-standard
latex only occurs in parts of the text which have not changed.
=item B<--label=label> or
B<-L label>
Sets the labels used to describe the old and new files. The first use
of this option sets the label describing the old file and the second
use of the option sets the label for the new file, i.e. set both
labels like this C<-L labelold -L labelnew>.
[Default: use the filename and modification dates for the label]
=item B<--no-label>
Suppress inclusion of old and new file names as comment in output file
=item B<--visble-label>
Include old and new filenames (or labels set with --label option) as
visible output.
=item B<--flatten>
Replace C<\input> and C<\include> commands within body by the content
of the files in their argument. If C<\includeonly> is present in the
preamble, only those files are expanded into the document. However,
no recursion is done, i.e. C<\input> and C<\include> commands within
included sections are not expanded. The included files are assumed to
be located in the same directories as the old and new master files,
respectively, making it possible to organise files into old and new directories.
--flatten is applied recursively, so inputted files can contain further
C<\input> statements.
Use of this option might result in prohibitive processing times for
larger documents, and the resulting difference document
no longer reflects the structure of the input documents.
=item B<--help> or
B<-h>
Show help text
=item B<--version>
Show version number
=back
=head2 Predefined styles
=head2 Major types
The major type determine the markup of plain text and some selected latex commands outside floats by defining the markup commands C<\DIFadd{...}> and C<\DIFdel{...}> .
=over 10
=item C<UNDERLINE>
Added text is wavy-underlined and blue, discarded text is struck out and red
(Requires color and ulem packages). Overstriking does not work in displayed math equations such that deleted parts of equation are underlined, not struck out (this is a shortcoming inherent to the ulem package).
=item C<CTRADITIONAL>
Added text is blue and set in sans-serif, and a red footnote is created for each discarded
piece of text. (Requires color package)
=item C<TRADITIONAL>
Like C<CTRADITIONAL> but without the use of color.
=item C<CFONT>
Added text is blue and set in sans-serif, and discarded text is red and very small size.
=item C<FONTSTRIKE>
Added tex is set in sans-serif, discarded text small and struck out
=item C<CCHANGEBAR>
Added text is blue, and discarded text is red. Additionally, the changed text is marked with a bar in the margin (Requires color and changebar packages).
=item C<CFONTCHBAR>
Like C<CFONT> but with additional changebars (Requires color and changebar packages).
=item C<CULINECHBAR>
Like C<UNDERLINE> but with additional changebars (Requires color, ulem and changebar packages).
=item C<CHANGEBAR>
No mark up of text, but mark margins with changebars (Requires changebar package).
=item C<INVISIBLE>
No visible markup (but generic markup commands will still be inserted.
=back
=head2 Subtypes
The subtype defines the commands that are inserted at the begin and end of added or discarded blocks, irrespectively of whether these blocks contain text or commands (Defined commands: C<\DIFaddbegin, \DIFaddend, \DIFdelbegin, \DIFdelend>)
=over 10
=item C<SAFE>
No additional markup (Recommended choice)
=item C<MARGIN>
Mark beginning and end of changed blocks with symbols in the margin nearby (using
the standard C<\marginpar> command - note that this sometimes moves somewhat
from the intended position.
=item C<COLOR>
An alternative way of marking added passages in blue, and deleted ones in red.
(It is recommeneded to use instead the main types to effect colored markup,
although in some cases coloring with dvipscol can be more complete, for example
with citation commands).
=item C<DVIPSCOL>
An alternative way of marking added passages in blue, and deleted ones in red. Note
that C<DVIPSCOL> only works with the dvips converter, e.g. not pdflatex.
(it is recommeneded to use instead the main types to effect colored markup,
although in some cases coloring with dvipscol can be more complete).
=back
=head2 Float Types
Some of the markup used in the main text might cause problems when used within
floats (e.g. figures or tables). For this reason alternative versions of all
markup commands are used within floats. The float type defines these alternative commands.
=over 10
=item C<FLOATSAFE>
Use identical markup for text as in the main body, but set all commands marking the begin and end of changed blocks to null-commands. You have to choose this float type if your subtype is C<MARGIN> as C<\marginpar> does not work properly within floats.
=item C<TRADITIONALSAFE>
Mark additions the same way as in the main text. Deleted environments are marked by angular brackets \[ and \] and the deleted text is set in scriptscript size. This float type should always be used with the C<TRADITIONAL> and C<CTRADITIONAL> markup types as the \footnote command does not work properly in floating environments.
=item C<IDENTICAL>
Make no difference between the main text and floats.
=back
=head2 Configuration Variables
=over 10
=item C<MINWORDSBLOCK>
Minimum number of tokens required to form an independent block. This value is
used in the algorithm to detect changes of complete blocks by merging identical text parts of less than C<MINWORDSBLOCK> to the preceding added and discarded parts.
[ Default: 3 ]
=item C<FLOATENV>
Environments whose name matches the regular expression in C<FLOATENV> are
considered floats. Within these environments, the I<latexdiff> markup commands
are replaced by their FL variaties.
[ Default: S<C<(?:figure|table|plate)[\w\d*@]*> >]
=item C<PICTUREENV>
Within environments whose name matches the regular expression in C<PICTUREENV>
all latexdiff markup is removed (in pathologic cases this might lead to
inconsistent markup but this situation should be rare).
[ Default: S<C<(?:picture|DIFnomarkup)[\w\d*@]*> >]
=item C<MATHENV>,C<MATHREPL>
If both \begin and \end for a math environment (environment name matching C<MATHENV>
or \[ and \])
are within the same deleted block, they are replaced by a \begin and \end commands for C<MATHREPL>
rather than being commented out.
[ Default: C<MATHENV>=S<C<(?:displaymath|equation)> >, C<MATHREPL>=S<C<displaymath> >]
=item C<MATHARRENV>,C<MATHARRREPL>
as C<MATHENV>,C<MATHREPL> but for equation arrays
[ Default: C<MATHARRENV>=S<C<eqnarray\*?> >, C<MATHREPL>=S<C<eqnarray> >]
=item C<ARRENV>
If a match to C<ARRENV> is found within an inline math environment within a deleted or added block, then the inlined math
is surrounded by C<\mbox{>...C<}>. This is necessary as underlining does not work within inlined array environments.
[ Default: C<ARRENV>=S<C<(?:array|[pbvBV]matrix)> >
=item C<COUNTERCMD>
If a command in a deleted block which is also in the textcmd list matches C<COUNTERCMD> then an
additional command C<\addtocounter{>F<cntcmd>C<}{-1}>, where F<cntcmd> is the matching command, is appended in the diff file such that the numbering in the diff file remains synchronized with the
numbering in the new file.
[ Default: C<COUNTERCMD>=C<(?:footnote|part|section|subsection> ...
C<|subsubsection|paragraph|subparagraph)> ]
=back
=head1 COMMON PROBLEMS
=over 10
=item Citations result in overfull boxes
There is an incompatibility between the C<ulem> package, which C<latexdiff> uses for underlining and striking out in the UNDERLINE style,
the default style. In order to be able to mark up citations properly, they are placed with an C<\mbox> command in post-processing. As mboxes
cannot be broken across lines, this procedure frequently results in overfull boxes, possibly obscuring the content as it extends beyond the right margin. If this is a problem, you have two possibilities:
1. Use C<COLOR> or C<DVIPSCOL> subtype markup (option C<-s COLOR>): If this markup is chosen, then changed citations are no longer marked up
with the wavy line (additions) or struck out (deletions), but are still highlighted in the appropriate color.
2. Choose option C<--disable-citation-markup> which turns off the marking up of citations: deleted citations are no longer shown, and
added ctations are shown without markup. (This was the default behaviour of latexdiff at versions 0.6 and older)
=item Changes in complicated mathematical equations result in latex processing errors
Try options C<--math-markup=whole>. If even that fails, you can turn off mark up for equations with C<--math-markup=off>.
=back
=head1 BUGS
Option allow-spaces not implemented entirely consistently. It breaks
the rules that number and type of white space does not matter, as
different numbers of inter-argument spaces are treated as significant.
Please submit bug reports using the issue tracker of the github repository page I<https://github.com/ftilmann/latexdiff.git>,
or send them to I<tilmann@gfz-potsdam.de>. Include the serial number of I<latexdiff>
(from comments at the top of the source or use B<--version>). If you come across latex
files that are error-free and conform to the specifications set out
above, and whose differencing still does not result in error-free
latex, please send me those files, ideally edited to only contain the
offending passage as long as that still reproduces the problem. If your
file relies on non-standard class files, you must include those. I will not
look at examples where I have trouble to latex the original files.
=head1 SEE ALSO
L<latexrevise>, L<latexdiff-vc>
=head1 PORTABILITY
I<latexdiff> does not make use of external commands and thus should run
on any platform supporting Perl 5.6 or higher. If files with encodings
other than ASCII or UTF-8 are processed, Perl 5.8 or higher is required.
The standard version of I<latexdiff> requires installation of the Perl package
C<Algorithm::Diff> (available from I<www.cpan.org> -
I<http://search.cpan.org/~nedkonz/Algorithm-Diff-1.15>) but a stand-alone
version, I<latexdiff-so>, which has this package inlined, is available, too.
I<latexdiff-fast> requires the I<diff> command to be present.
=head1 AUTHOR
Version 1.0.4
Copyright (C) 2004-2012 Frederik Tilmann
This program is free software; you can redistribute it and/or modify
it under the terms of the GNU General Public License Version 3
Contributors of fixes and additions: V. Kuhlmann, J. Paisley, N. Becker, T. Doerges, K. Huebner,
T. Connors, Sebastian Gouezel and many others.
Thanks to the many people who sent in bug reports, feature suggestions, and other feedback.
=cut
__END__
%%BEGIN SAFE COMMANDS
% Regex matching commands which can safely be in the
% argument of a \DIFadd or \DIFdel command (leave out the \)
arabic
dashbox
emph
fbox
framebox
hspace
math.*
makebox
mbox
pageref
ref
symbol
raisebox
rule
text.*
shortstack
usebox
dag
ddag
copyright
pounds
S
P
oe
OE
ae
AE
aa
AA
o
O
l
L
frac
ss
sqrt
ldots
cdots
vdots
ddots
alpha
beta
gamma
delta
epsilon
varepsilon
zeta
eta
theta
vartheta
iota
kappa
lambda
mu
nu
xi
pi
varpi
rho
varrho
sigma
varsigma
tau
upsilon
phi
varphi
chi
psi
omega
Gamma
Delta
Theta
Lambda
Xi
Pi
Sigma
Upsilon
Phi
Psi
Omega
ps
mp
times
div
ast
star
circ
bullet
cdot
cap
cup
uplus
sqcap
vee
wedge
setminus
wr
diamond
(?:big)?triangle.*
lhd
rhd
unlhd
unrhd
oplus
ominus
otimes
oslash
odot
bigcirc
d?dagger
amalg
leq
prec
preceq
ll
(?:sq)?su[bp]set(?:eq)?
in
vdash
geq
succ(?:eq)?
gg
ni
dashv
equiv
sim(?:eq)?
asymp
approx
cong
neq
doteq
propto
models
perp
mid
parallel
bowtie
Join
smile
frown
.*arrow
(?:long)?mapsto
.*harpoon.*
leadsto
aleph
hbar
imath
jmath
ell
wp
Re
Im
mho
prime
emptyset
nabla
surd
top
bot
angle
forall
exists
neg
flat
natural
sharp
backslash
partial
infty
Box
Diamond
triangle
clubsuit
diamondsuit
heartsuit
spadesuit
sum
prod
coprod
int
oint
big(?:sq)?c[au]p
bigvee
bigwedge
bigodot
bigotimes
bigoplus
biguplus
(?:arc)?(?:cos|sin|tan|cot)h?
csc
arg
deg
det
dim
exp
gcd
hom
inf
ker
lg
lim
liminf
limsup
ln
log
max
min
Pr
sec
sup
[Hclbdruvt]
(SUPER|SUB)SCRIPTNB
(SUPER|SUB)SCRIPT
PERCENTAGE
DOLLAR
%%END SAFE COMMANDS
%%BEGIN TEXT COMMANDS
% Regex matching commands with a text argument (leave out the \)
addcontents.*
cc
closing
chapter
dashbox
emph
encl
fbox
framebox
footnote
footnotetext
framebox
part
(sub){0,2}section\*?
(sub)?paragraph\*?
makebox
mbox
opening
parbox
raisebox
savebox
sbox
shortstack
signature
text.*
value
underline
sqrt
(SUPER|SUB)SCRIPT
%%END TEXT COMMANDS
%%BEGIN CONTEXT1 COMMANDS
% Regex matching commands with a text argument (leave out the \), which will fail out of context, but whose argument should be printed as plain text
caption
%%END CONTEXT1 COMMANDS
%%BEGIN CONTEXT2 COMMANDS
% Regex matching commands with a text argument (leave out the \), which will fail out of context, but whose argument should be printed as plain text
title
author
date
institute
%%END CONTEXT2 COMMANDS
%% TYPES (Commands for highlighting changed blocks)
%DIF UNDERLINE PREAMBLE
\RequirePackage[normalem]{ulem}
\RequirePackage{color}\definecolor{RED}{rgb}{1,0,0}\definecolor{BLUE}{rgb}{0,0,1}
\providecommand{\DIFadd}[1]{{\protect\color{blue}\uwave{#1}}}
\providecommand{\DIFdel}[1]{{\protect\color{red}\sout{#1}}}
%DIF END UNDERLINE PREAMBLE
%DIF CTRADITIONAL PREAMBLE
\RequirePackage{color}\definecolor{RED}{rgb}{1,0,0}\definecolor{BLUE}{rgb}{0,0,1}
\RequirePackage[stable]{footmisc}
\providecommand{\DIFadd}[1]{{\protect\color{blue} \sf #1}}
\providecommand{\DIFdel}[1]{{\protect\color{red} [..\footnote{removed: #1} ]}}
%DIF END CTRADITIONAL PREAMBLE
%DIF TRADITIONAL PREAMBLE
\RequirePackage[stable]{footmisc}
\providecommand{\DIFadd}[1]{{\sf #1}}
\providecommand{\DIFdel}[1]{{[..\footnote{removed: #1} ]}}
%DIF END TRADITIONAL PREAMBLE
%DIF CFONT PREAMBLE
\RequirePackage{color}\definecolor{RED}{rgb}{1,0,0}\definecolor{BLUE}{rgb}{0,0,1}
\providecommand{\DIFadd}[1]{{\protect\color{blue} \sf #1}}
\providecommand{\DIFdel}[1]{{\protect\color{red} \scriptsize #1}}
%DIF END CFONT PREAMBLE
%DIF FONTSTRIKE PREAMBLE
\RequirePackage[normalem]{ulem}
\providecommand{\DIFadd}[1]{{\sf #1}}
\providecommand{\DIFdel}[1]{{\footnotesize \sout{#1}}}
%DIF END FONTSTRIKE PREAMBLE
%DIF CCHANGEBAR PREAMBLE
\RequirePackage[dvips]{changebar}
\RequirePackage{color}\definecolor{RED}{rgb}{1,0,0}\definecolor{BLUE}{rgb}{0,0,1}
\providecommand{\DIFadd}[1]{\protect\cbstart{\protect\color{blue}#1}\protect\cbend}
\providecommand{\DIFdel}[1]{\protect\cbdelete{\protect\color{red}#1}\protect\cbdelete}
%DIF END CCHANGEBAR PREAMBLE
%DIF CFONTCHBAR PREAMBLE
\RequirePackage[dvips]{changebar}
\RequirePackage{color}\definecolor{RED}{rgb}{1,0,0}\definecolor{BLUE}{rgb}{0,0,1}
\providecommand{\DIFadd}[1]{\protect\cbstart{\protect\color{blue}\sf #1}\protect\cbend}
\providecommand{\DIFdel}[1]{\protect\cbdelete{\protect\color{red}\scriptsize #1}\protect\cbdelete}
%DIF END CFONTCHBAR PREAMBLE
%DIF CULINECHBAR PREAMBLE
\RequirePackage[normalem]{ulem}
\RequirePackage[dvips]{changebar}
\RequirePackage{color}
\providecommand{\DIFadd}[1]{\protect\cbstart{\protect\color{blue}\uwave{#1}}\protect\cbend}
\providecommand{\DIFdel}[1]{\protect\cbdelete{\protect\color{red}\sout{#1}}\protect\cbdelete}
%DIF END CULINECHBAR PREAMBLE
%DIF CHANGEBAR PREAMBLE
\RequirePackage[dvips]{changebar}
\providecommand{\DIFadd}[1]{\protect\cbstart{#1}\protect\cbend}
\providecommand{\DIFdel}[1]{\protect\cbdelete}
%DIF END CHANGEBAR PREAMBLE
%DIF INVISIBLE PREAMBLE
\providecommand{\DIFadd}[1]{#1}
\providecommand{\DIFdel}[1]{}
%DIF END INVISIBLE PREAMBLE
%% SUBTYPES (Markers for beginning and end of changed blocks)
%DIF SAFE PREAMBLE
\providecommand{\DIFaddbegin}{}
\providecommand{\DIFaddend}{}
\providecommand{\DIFdelbegin}{}
\providecommand{\DIFdelend}{}
%DIF END SAFE PREAMBLE
%DIF MARGIN PREAMBLE
\providecommand{\DIFaddbegin}{\protect\marginpar{a[}}
\providecommand{\DIFaddend}{\protect\marginpar{]}}
\providecommand{\DIFdelbegin}{\protect\marginpar{d[}}
\providecommand{\DIFdelend}{\protect\marginpar{]}}
%DIF END BRACKET PREAMBLE
%DIF DVIPSCOL PREAMBLE
%Note: only works with dvips converter
\RequirePackage{color}
\RequirePackage{dvipscol}
\providecommand{\DIFaddbegin}{\protect\nogroupcolor{blue}}
\providecommand{\DIFaddend}{\protect\nogroupcolor{black}}
\providecommand{\DIFdelbegin}{\protect\nogroupcolor{red}}
\providecommand{\DIFdelend}{\protect\nogroupcolor{black}}
%DIF END DVIPSCOL PREAMBLE
%DIF COLOR PREAMBLE
\RequirePackage{color}
\providecommand{\DIFaddbegin}{\protect\color{blue}}
\providecommand{\DIFaddend}{\protect\color{black}}
\providecommand{\DIFdelbegin}{\protect\color{red}}
\providecommand{\DIFdelend}{\protect\color{black}}
%DIF END COLOR PREAMBLE
%DIF LABEL PREAMBLE
% To show only pages with changes (pdf) (external program pdftk needs to be installed)
% (only works for simple documents with non-repeated page numbers)
% pdflatex diff.tex
% pdflatex diff.tex
% pdftk diff.pdf cat `perl -lne 'if (m/\\newlabel{DIFchg[be]\d*}{{.*}{(.*)}}/) { print $1 }' diff.aux | uniq | tr -s \\n ' '` output diff-changedpages.pdf
% To show only pages with changes (dvips/dvipdf)
% latex diff.tex
% latex diff.tex
% dvips -pp `perl -lne 'if (m/\\newlabel{DIFchg[be]\d*}{{.*}{(.*)}}/) { print $1 }' diff.aux | uniq | tr -s \\n ','` diff.dvi
\typeout{Check comments in preamble of output for instructions how to show only pages where changes have been made}
\newcount\DIFcounterb
\global\DIFcounterb 0\relax
\newcount\DIFcountere
\global\DIFcountere 0\relax
\providecommand{\DIFaddbegin}{\global\advance\DIFcounterb 1\relax\label{DIFchgb\the\DIFcounterb}} %DIF PREAMBLE
\providecommand{\DIFaddend}{\global\advance\DIFcountere 1\relax\label{DIFchge\the\DIFcountere}} %DIF PREAMBLE
\providecommand{\DIFdelbegin}{\global\advance\DIFcounterb 1\relax\label{DIFchgb\the\DIFcounterb}} %DIF PREAMBLE
\providecommand{\DIFdelend}{\global\advance\DIFcountere 1\relax\label{DIFchge\the\DIFcountere}} %DIF PREAMBLE
%DIF END LABEL PREAMBLE
%% FLOAT TYPES
%DIF FLOATSAFE PREAMBLE
\providecommand{\DIFaddFL}[1]{\DIFadd{#1}}
\providecommand{\DIFdelFL}[1]{\DIFdel{#1}}
\providecommand{\DIFaddbeginFL}{}
\providecommand{\DIFaddendFL}{}
\providecommand{\DIFdelbeginFL}{}
\providecommand{\DIFdelendFL}{}
%DIF END FLOATSAFE PREAMBLE
%DIF IDENTICAL PREAMBLE
\providecommand{\DIFaddFL}[1]{\DIFadd{#1}}
\providecommand{\DIFdelFL}[1]{\DIFdel{#1}}
\providecommand{\DIFaddbeginFL}{\DIFaddbegin}
\providecommand{\DIFaddendFL}{\DIFaddend}
\providecommand{\DIFdelbeginFL}{\DIFdelbegin}
\providecommand{\DIFdelendFL}{\DIFdelend}
%DIF END IDENTICAL PREAMBLE
%DIF TRADITIONALSAFE PREAMBLE
% procidecommand color to make this work for TRADITIONAL and CTRADITIONAL
\providecommand{\color}[1]{}
\providecommand{\DIFaddFL}[1]{\DIFadd{#1}}
\providecommand{\DIFdel}[1]{{\protect\color{red}[..{\scriptsize {removed: #1}} ]}}
\providecommand{\DIFaddbeginFL}{}
\providecommand{\DIFaddendFL}{}
\providecommand{\DIFdelbeginFL}{}
\providecommand{\DIFdelendFL}{}
%DIF END TRADITIONALSAFE PREAMBLE
%% SPECIAL PACKAGE PREAMBLE COMMANDS
% Standard \DIFadd and \DIFdel are redefined as \DIFaddtex and \DIFdeltex
% when hyperref package is included.
%DIF HYPERREF PREAMBLE
\providecommand{\DIFadd}[1]{\texorpdfstring{\DIFaddtex{#1}}{#1}}
\providecommand{\DIFdel}[1]{\texorpdfstring{\DIFdeltex{#1}}{}}
%DIF END HYPERREF PACKAGE
|