From ebd49895acbb9983700fd9d54959dbeda259b086 Mon Sep 17 00:00:00 2001 From: Takuji Tanaka Date: Sun, 19 Sep 2021 08:57:18 +0000 Subject: upmendex: modify heuristic detection of page number types git-svn-id: svn://tug.org/texlive/trunk@60549 c570f23f-e606-0410-a88d-b1316a301751 --- Build/source/texk/upmendex/ChangeLog | 8 ++++++++ Build/source/texk/upmendex/fread.c | 24 ++++++++++++++---------- Build/source/texk/upmendex/tests/pprec3.ist | 11 +++++++++++ Build/source/texk/upmendex/tests/pprec4.ist | 11 +++++++++++ Build/source/texk/upmendex/tests/pprecB-0.ind | 5 +++++ Build/source/texk/upmendex/tests/pprecB-3.ind | 5 +++++ Build/source/texk/upmendex/tests/pprecB-4.ind | 5 +++++ Build/source/texk/upmendex/tests/pprecB.idx | 9 +++++++++ Build/source/texk/upmendex/tests/range.idx | 14 +++++++------- Build/source/texk/upmendex/tests/range1.ind | 4 ++-- Build/source/texk/upmendex/tests/range2.ind | 4 ++-- Build/source/texk/upmendex/tests/range3.ind | 4 ++-- Build/source/texk/upmendex/tests/upmendex.test | 14 +++++++++++++- 13 files changed, 94 insertions(+), 24 deletions(-) create mode 100644 Build/source/texk/upmendex/tests/pprec3.ist create mode 100644 Build/source/texk/upmendex/tests/pprec4.ist create mode 100644 Build/source/texk/upmendex/tests/pprecB-0.ind create mode 100644 Build/source/texk/upmendex/tests/pprecB-3.ind create mode 100644 Build/source/texk/upmendex/tests/pprecB-4.ind create mode 100644 Build/source/texk/upmendex/tests/pprecB.idx (limited to 'Build/source/texk/upmendex') diff --git a/Build/source/texk/upmendex/ChangeLog b/Build/source/texk/upmendex/ChangeLog index 045305ef8c9..65c5ba4519a 100644 --- a/Build/source/texk/upmendex/ChangeLog +++ b/Build/source/texk/upmendex/ChangeLog @@ -1,3 +1,11 @@ +2021-09-19 TANAKA Takuji + + * fread.c: + Modify heuristic detection of page number types. + * tests/upmendex.test, tests/range.idx, tests/range[123].ind, + tests/pprecB.idx, tests/pprec[34].ist, tests/pprecB-[034].ind: + Update tests. + 2021-09-18 TANAKA Takuji * fread.c, fwrite.c, sort.c, mendex.h, {,ex}var.h: diff --git a/Build/source/texk/upmendex/fread.c b/Build/source/texk/upmendex/fread.c index ba1d3514856..66d3e0b1449 100644 --- a/Build/source/texk/upmendex/fread.c +++ b/Build/source/texk/upmendex/fread.c @@ -344,7 +344,7 @@ LOOP: copy_multibyte_char(buff, table, &j, &k); } - table[k]='\0'; + table[k]='\0'; for (k=0;k<=ind[l].num;k++) { if (strcmp(ind[l].p[k].page,table)==0) { @@ -356,9 +356,9 @@ LOOP: ind[l].num++; if (!((ind[l].num)%16)) ind[l].p=(struct page *)xrealloc(ind[l].p,sizeof(struct page)*((int)((ind[l].num)/16)+1)*16); - ind[l].p[ind[l].num].page=xstrdup(table); + ind[l].p[ind[l].num].page=xstrdup(table); - ind[l].p[ind[l].num].enc=xstrdup(estr); + ind[l].p[ind[l].num].enc=xstrdup(estr); chkpageattr(&ind[l].p[ind[l].num]); } } @@ -388,15 +388,15 @@ LOOP: nest++; if (buff[j]==arg_close) { if (nest==0) { - table[k]='\0'; - ind[i].p[0].page=xstrdup(table); + table[k]='\0'; + ind[i].p[0].page=xstrdup(table); break; } else nest--; } copy_multibyte_char(buff, table, &j, &k); } - ind[l].p[0].enc=xstrdup(estr); + ind[l].p[0].enc=xstrdup(estr); chkpageattr(&ind[i].p[0]); } } @@ -538,7 +538,7 @@ ATTRLOOP: switch(page_precedence[pattr[cc]]) { case 'r': if (strchr("ivxlcdm",*page0)==NULL || - (strchr("lcdm",*page0) && strchr(page_precedence,'a') && strlen(buff)==1 && pcpos)) { + (strchr("lcdm",*page0) && strchr(page_precedence,'a') && strlen(buff)==1 && pcpos)) { /* heuristic detection as alphabet since L=50, C=100, D=100, M=1000 are quite large */ if (pattr[cc]'z' || strlen(buff)>1) { + if (*page0<'a' || *page0>'z' || strlen(buff)>1 || + (strchr("ivx",*page0) && strchr(page_precedence,'r') && !pcpos)) { + /* heuristic detection as roman number since I=1, V=5, X=10 are quite small */ if (pattr[cc]'Z' || strlen(buff)>1) { + if (*page0<'A' || *page0>'Z' || strlen(buff)>1 || + (strchr("IVX",*page0) && strchr(page_precedence,'R') && !pcpos)) { + /* heuristic detection as roman number since I=1, V=5, X=10 are quite small */ if (pattr[cc]