summaryrefslogtreecommitdiff
path: root/Master/texmf-dist/scripts/citation-style-language/citeproc-bib.lua
blob: d3532c098be1e24fff397f9b6f4fa7902dec851f (plain)
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
--[[
  A naive implementation of a Bib(La)TeX dateabase (.bib) parser
  References:
  - http://mirrors.ctan.org/biblio/bibtex/base/btxdoc.pdf
  - http://mirrors.ctan.org/info/bibtex/tamethebeast/ttb_en.pdf
  - https://github.com/brechtm/citeproc-py/blob/master/citeproc/source/bibtex/bibparse.py
  - http://maverick.inria.fr/~Xavier.Decoret/resources/xdkbibtex/bibtex_summary.html
  - https://github.com/pcooksey/bibtex-js/blob/master/src/bibtex_js.js
--]]

local bib = {}

require("lualibs")
local unicode = require("unicode")

local util = require("citeproc-util")


local path = "citeproc-bib-data.json"
if kpse then
  path = kpse.find_file(path)
end
if path then
  local contents = util.read_file(path)
  if not contents then
    error(string.format('Failed to find "%s"', path))
  end
  bib.bib_data = utilities.json.tolua(contents)
end

function bib.parse(contents)
  local items = {}
  for item_contents in string.gmatch(contents, "(@%w+%b{})") do
    local item = bib.parse_item(item_contents)
    table.insert(items, item)
  end
  return items
end

function bib.parse_item(contents)
  contents = string.gsub(contents, "%s*\r?\n%s*", " ")
  local bib_type, id
  bib_type, id, contents = string.match(contents, "^@(%w+){([^%s,]+),%s*(.*)}$")
  if not id then
    return nil
  end

  local item = {id = id}

  bib_type = string.lower(bib_type)
  local type_data = bib.bib_data.types[bib_type]
  if type_data then
    if type_data.csl then
      item.type = type_data.csl
    else
      item.type = "document"
    end
  else
    item.type = "document"
  end

  local bib_fields = bib.parse_fields(contents)
  -- util.debug(bib_fields)

  for bib_field, value in pairs(bib_fields) do
    local csl_field, csl_value = bib.convert_field(bib_field, value)

    if csl_field and not item[csl_field] then
      item[csl_field] = csl_value
    end
  end

  bib.process_special_fields(item, bib_fields)

  return item
end

function bib.parse_fields(contents)
  local fields = {}
  local field_patterns = {
    "^(%w+)%s*=%s*(%b{}),?%s*(.-)$",
    '^(%w+)%s*=%s*"([^"]*)",?%s*(.-)$',
    "^(%w+)%s*=%s*(%w+),?%s*(.-)$",
  }

  while #contents > 0 do
    local field, value, rest
    -- This pattern may fail in the case of `title = {foo\}bar}`.
    for pattern_index, pattern in ipairs(field_patterns) do
      field, value, rest = string.match(contents, pattern)
      if value then
        if pattern_index == 1 then
          -- Strip braces "{}"
          value = string.sub(value, 2, -2)
        elseif pattern_index == 3 then
          if not string.match(value, "^%d+$") then
            local string_name = value
            local macro = bib.bib_data.macros[string_name]
            if macro then
              value = macro.value
            else
              util.warning(string.format('String name "%s" is undefined', string_name))
            end
          end
        end
        fields[field] = value
        contents = rest
        break
      end
    end
  end
  return fields
end

function bib.convert_field(bib_field, value)
  local field_data = bib.bib_data.fields[bib_field]
  if not field_data then
    return nil, nil
  end
  local csl_field = field_data.csl
  if not csl_field then
    return nil, nil
  end

  value = bib.unescape(bib_field, value)

  local field_type = field_data.type
  if field_type == "name" then
    value = bib.parse_names(value)
  elseif field_type == "date" then
    value = bib.parse_date(value)
  end

  if bib_field == "title" or bib_field == "booktitle" then
    -- TODO: check if the original title is in sentence case
    value = bib.convert_sentence_case(value)
  end

  if bib_field == "volume" or bib_field == "pages" then
    value = string.gsub(value, util.unicode["en dash"], "-")
  end

  return csl_field, value
end

function bib.unescape(field, str)
  str = string.gsub(str, "%-%-%-", util.unicode["em dash"])
  str = string.gsub(str, "%-%-", util.unicode["en dash"])
  str = string.gsub(str, "``", util.unicode["left double quotation mark"])
  str = string.gsub(str, "''", util.unicode["right double quotation mark"])
  str = string.gsub(str, "`", util.unicode["left single quotation mark"])
  str = string.gsub(str, "'", util.unicode["right single quotation mark"])
  -- TODO: unicode chars like \"{o}
  str = string.gsub(str, "\\#", "#")
  str = string.gsub(str, "\\%$", "$")
  str = string.gsub(str, "\\%%", "%")
  str = string.gsub(str, "\\&", "&")
  str = string.gsub(str, "\\{", "{")
  str = string.gsub(str, "\\}", "}")
  str = string.gsub(str, "\\_", "_")
  if field ~= "url" then
    str = string.gsub(str, "~", util.unicode["no-break space"])
  end
  str = string.gsub(str, "\\quad%s+", util.unicode["em space"])
  return str
end

function bib.convert_sentence_case(str)
  local res = ""
  local to_lower = false
  local brace_level = 0
  for _, code_point in utf8.codes(str) do
    local char = utf8.char(code_point)
    if to_lower and brace_level == 0 then
      char = unicode.utf8.lower(char)
    end
    if string.match(char, "%S") then
      to_lower = true
    end
    if char == "{" then
      brace_level = brace_level + 1
      char = ""
    elseif char == "}" then
      brace_level = brace_level - 1
      char = ""
    elseif char == ":" then
      to_lower = false
    end
    res = res .. char
  end
  return res
end

function bib.parse_names(str)
   -- "{International Federation of Library Association and Institutions}"
  local names = {}
  local brace_level = 0
  local name = ""
  local last_word = ""
  for i = 1, #str do
    local char = string.sub(str, i, i)
    if char == " " then
      if brace_level == 0 and last_word == "and" then
        table.insert(names, name)
        name = ""
      else
        if name ~= "" then
          name = name .. " "
        end
        name = name .. last_word
      end
      last_word = ""
    else
      last_word = last_word .. char
      if char == "{" then
        brace_level = brace_level + 1
      elseif char == "}" then
        brace_level = brace_level - 1
      end
    end
  end

  if name ~= "" then
    name = name .. " "
  end
  name = name .. last_word
  table.insert(names, name)

  for i, name in ipairs(names) do
    names[i] = bib.parse_single_name(name)
  end
  return names
end

function bib.parse_single_name(str)
  local literal = string.match(str, "^{(.*)}$")
  if literal then
    return {
      literal = literal,
    }
  end

  local name_parts = util.split(str, ",%s*")
  if #name_parts > 1 then
    return bib.parse_revesed_name(name_parts)
  else
    return bib.parse_non_revesed_name(str)
  end
end

function bib.parse_revesed_name(name_parts)
  local name = {}
  local von, last, jr, first
  if #name_parts == 2 then
    first = name_parts[2]
  elseif #name_parts >= 3 then
    jr = name_parts[2]
    first = name_parts[3]
  end
  if first and first ~= "" then
    name.given = first
  end
  if jr and jr ~= "" then
    name.suffix = jr
  end

  last = name_parts[1]
  local words = util.split(last)
  local index = #words - 1
  while index > 0 and string.match(words[index], "^%L") do
    index = index - 1
  end
  name.family = util.concat(util.slice(words, index + 1), " ")
  if index >= 1 then
    von = util.concat(util.slice(words, 1, index), " ")
    name["non-dropping-particle"] = von
  end
  return name
end

function bib.parse_non_revesed_name(str)
  local name = {}
  local words = util.split(str)

  local index = 1
  -- TODO: case determination for pseudo-characters (e.g., "\bb{BB}")
  while index < #words and string.match(words[index], "^%L") do
    index = index + 1
  end
  if index > 1 then
    name.given = util.concat(util.slice(words, 1, index - 1), " ")
  end

  local particle_start_index = index
  index = #words - 1
  while index >= particle_start_index and string.match(words[index], "^%L") do
    index = index - 1
  end
  if index >= particle_start_index then
    local particles = util.slice(words, particle_start_index, index)
    -- TODO: distiguish dropping and non-dropping particles
    name["non-dropping-particle"] = util.concat(particles, " ")
  end
  name.family = util.concat(util.slice(words, index + 1), " ")

  return name
end

function bib.parse_date(str)
  local date_range = util.split(str, "/")
  if #date_range == 1 then
    date_range = util.split(str, util.unicode["en dash"])
  end

  local literal = { literal = str }

  if #date_range > 2 then
    return literal
  end

  local date = {}
  date["date-parts"] = {}
  for _, date_part in ipairs(date_range) do
    local date_ = bib.parse_single_date(date_part)
    if not date_ then
      return literal
    end
    table.insert(date["date-parts"], date_)
  end
  return date
end

function bib.parse_single_date(str)
  local date = {}
  for _, date_part in ipairs(util.split(str, "%-")) do
    if not string.match(date_part, "^%d+$") then
      return nil
    end
    table.insert(date, tonumber(date_part))
  end
  return date
end

function bib.process_special_fields(item, bib_fields)
  if item.type == "document" then
    if item.URL then
      item.type = "webpage"
    else
      item.type = "article"
    end
  end

  if item.type == "article-journal" then
    if not item["container-title"] then
      item.type = "article"
    end
  end

  if bib_fields.year and not item.issued then
    item.issued = bib.parse_date(bib_fields.year)
  end
  local month = bib_fields.month
  if month and string.match(month, "^%d+$") then
    if item.issued and item.issued["date-parts"] and
        item.issued["date-parts"][1] and
        item.issued["date-parts"][1][2] == nil then
      item.issued["date-parts"][1][2] = tonumber(month)
    end
  end

  if item.number then
    if not item.issue and item.type == "article-journal" or item.type == "article-magazine" or item.type == "article-newspaper" or item.type == "periodical" then
      item.issue = item.number
      item.number = nil
    elseif item.type == "patent" or item.type == "report" or item.type == "standard" then
    else
      item["collection-number"] = item.number
      item.number = nil
    end
  end

  if not item.PMID and bib_fields.eprint and string.lower(bib_fields.eprinttype) == "pubmed" then
    item.PMID = bib_fields.eprint
  end

  -- if not item.language then
  --   if util.has_cjk_char(item.title) then
  --     item.language = "zh"
  --   else
  --     item.language = "en"
  --   end
  -- end
end

return bib