@retorquere/bibtex-parser 7.0.8 → 7.0.9

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (7) hide show
  1. package/grammar.d.ts +1 -1
  2. package/grammar.js +682 -601
  3. package/index.js +30 -29
  4. package/package.json +17 -17
  5. package/sentence-case.js +1 -1
  6. package/strings.bib +3243 -0
  7. package/unabbrev.json +29 -29
package/index.js CHANGED
@@ -148,7 +148,7 @@ exports.fields = {
148
148
  'file',
149
149
  'files',
150
150
  'pdf',
151
- 'groups',
151
+ 'groups', // jabref unilaterally decided to make this non-standard field verbatim
152
152
  'ids',
153
153
  'url',
154
154
  'verba',
@@ -299,7 +299,7 @@ class Parser {
299
299
  ast(input, clean = true) {
300
300
  let parsed = [];
301
301
  for (const chunk of chunker.parse(input)) {
302
- const { children } = bibtex.parse(chunk.text, Object.assign(Object.assign({}, this.options), { combiningDiacritics: unicode2latex_1.diacritics.commands }));
302
+ const { children } = bibtex.parse(chunk.text, Object.assign(Object.assign({}, this.options), { combining: unicode2latex_1.combining.commands }));
303
303
  if (clean)
304
304
  this.clean(children);
305
305
  parsed = parsed.concat(children);
@@ -419,7 +419,7 @@ class Parser {
419
419
  parseChunk(chunk) {
420
420
  this.chunk = chunk.text;
421
421
  try {
422
- let bib = bibtex.parse(chunk.text, Object.assign(Object.assign({}, this.options), { combiningDiacritics: unicode2latex_1.diacritics.commands }));
422
+ let bib = bibtex.parse(chunk.text, Object.assign(Object.assign({}, this.options), { combining: unicode2latex_1.combining.commands }));
423
423
  if (bib.kind !== 'Bibliography')
424
424
  throw new Error(this.show(bib));
425
425
  bib = this.clean(bib);
@@ -704,14 +704,14 @@ class Parser {
704
704
  clean_script(node) {
705
705
  let m, value, singlechar;
706
706
  // recognize combined forms like \^\circ
707
- if (singlechar = unicode2latex_1.latex[node.source])
707
+ if (singlechar = unicode2latex_1.latex2unicode[node.source])
708
708
  return this.text(singlechar);
709
- if ((m = node.source.match(/^([\^_])([^{}]+)$/)) && ((singlechar = unicode2latex_1.latex[`${m[1]}${m[2]}`]) || (singlechar = unicode2latex_1.latex[`${m[1]}{${m[2]}}`])))
709
+ if ((m = node.source.match(/^([\^_])([^{}]+)$/)) && ((singlechar = unicode2latex_1.latex2unicode[`${m[1]}${m[2]}`]) || (singlechar = unicode2latex_1.latex2unicode[`${m[1]}{${m[2]}}`])))
710
710
  return this.text(singlechar);
711
- if ((m = node.source.match(/^([\^_])\{([^{}]+)\}$/)) && ((singlechar = unicode2latex_1.latex[`${m[1]}${m[2]}`]) || (singlechar = unicode2latex_1.latex[`${m[1]}{${m[2]}}`])))
711
+ if ((m = node.source.match(/^([\^_])\{([^{}]+)\}$/)) && ((singlechar = unicode2latex_1.latex2unicode[`${m[1]}${m[2]}`]) || (singlechar = unicode2latex_1.latex2unicode[`${m[1]}{${m[2]}}`])))
712
712
  return this.text(singlechar);
713
713
  const cmd = node.kind === 'SuperscriptCommand' ? '^' : '_';
714
- if (typeof node.value === 'string' && (singlechar = unicode2latex_1.latex[`${cmd}${node.value}`] || unicode2latex_1.latex[`${cmd}{${node.value}}`])) {
714
+ if (typeof node.value === 'string' && (singlechar = unicode2latex_1.latex2unicode[`${cmd}${node.value}`] || unicode2latex_1.latex2unicode[`${cmd}{${node.value}}`])) {
715
715
  return this.text(singlechar);
716
716
  }
717
717
  if (typeof node.value === 'string') {
@@ -767,13 +767,13 @@ class Parser {
767
767
  }
768
768
  clean_diacritic(node) {
769
769
  const char = node.dotless ? `\\${node.character}` : node.character;
770
- let unicode = unicode2latex_1.latex[`\\${node.mark}{${char}}`]
771
- || unicode2latex_1.latex[`\\${node.mark}${char}`]
772
- || unicode2latex_1.latex[`{\\${node.mark} ${char}}`]
773
- || unicode2latex_1.latex[`{\\${node.mark}${char}}`]
774
- || unicode2latex_1.latex[`\\${node.mark} ${char}`];
775
- if (!unicode && !node.dotless && node.character.length === 1 && unicode2latex_1.diacritics.tounicode[node.mark])
776
- unicode = node.character + unicode2latex_1.diacritics.tounicode[node.mark];
770
+ let unicode = unicode2latex_1.latex2unicode[`\\${node.mark}{${char}}`]
771
+ || unicode2latex_1.latex2unicode[`\\${node.mark}${char}`]
772
+ || unicode2latex_1.latex2unicode[`{\\${node.mark} ${char}}`]
773
+ || unicode2latex_1.latex2unicode[`{\\${node.mark}${char}}`]
774
+ || unicode2latex_1.latex2unicode[`\\${node.mark} ${char}`];
775
+ if (!unicode && !node.dotless && node.character.length === 1 && unicode2latex_1.combining.tounicode[node.mark])
776
+ unicode = node.character + unicode2latex_1.combining.tounicode[node.mark];
777
777
  if (!unicode && !this.in_preamble)
778
778
  return this.error(new TeXError(`Unhandled \\${node.mark}{${char}}`, node, this.chunk));
779
779
  return this.text(unicode);
@@ -781,7 +781,7 @@ class Parser {
781
781
  clean_symbol(node) {
782
782
  if (node.command === '\\')
783
783
  return this.text('\n');
784
- return this.text(unicode2latex_1.latex[`\\${node.command}`] || node.command);
784
+ return this.text(unicode2latex_1.latex2unicode[`\\${node.command}`] || node.command);
785
785
  }
786
786
  first_text_block(node) {
787
787
  if (!node)
@@ -809,7 +809,7 @@ class Parser {
809
809
  clean_command(node) {
810
810
  var _a;
811
811
  let arg, unicode;
812
- if (unicode = unicode2latex_1.latex[node.source])
812
+ if (unicode = unicode2latex_1.latex2unicode[node.source])
813
813
  return this.text(unicode);
814
814
  switch (node.command) {
815
815
  case 'newcommand':
@@ -827,7 +827,7 @@ class Parser {
827
827
  return { kind: 'Markup', value: '<li>', source: node.source };
828
828
  case 'frac':
829
829
  if (arg = this.argument(node, 2)) {
830
- if (arg[0].kind === 'Text' && arg[1].kind === 'Text' && (unicode = unicode2latex_1.latex[`\\frac{${arg[0].value}}{${arg[1].value}}`]))
830
+ if (arg[0].kind === 'Text' && arg[1].kind === 'Text' && (unicode = unicode2latex_1.latex2unicode[`\\frac{${arg[0].value}}{${arg[1].value}}`]))
831
831
  return this.text(unicode);
832
832
  return this.clean({
833
833
  kind: 'Block',
@@ -854,10 +854,11 @@ class Parser {
854
854
  case 'else':
855
855
  case 'fi':
856
856
  case 'makeatletter':
857
+ case 'mathslbb':
857
858
  return this.text();
858
859
  case 'ElsevierGlyph':
859
860
  if (arg = this.argument(node, 'Text')) {
860
- if (unicode = unicode2latex_1.latex[`\\${node.command}{${arg}}`])
861
+ if (unicode = unicode2latex_1.latex2unicode[`\\${node.command}{${arg}}`])
861
862
  return this.text(unicode);
862
863
  return this.text(String.fromCharCode(parseInt(arg, 16)));
863
864
  }
@@ -888,14 +889,14 @@ class Parser {
888
889
  break;
889
890
  case 'textsuperscript':
890
891
  case 'sp':
891
- if ((arg = this.argument(node, 'Text')) && (unicode = unicode2latex_1.latex[`^{${arg}}`]))
892
+ if ((arg = this.argument(node, 'Text')) && (unicode = unicode2latex_1.latex2unicode[`^{${arg}}`]))
892
893
  return this.text(unicode);
893
894
  if (arg = this.argument(node, 'Block'))
894
895
  return this.clean(arg);
895
896
  break;
896
897
  case 'textsubscript':
897
898
  case 'sb':
898
- if ((arg = this.argument(node, 'Text')) && (unicode = unicode2latex_1.latex[`_{${arg}}`]))
899
+ if ((arg = this.argument(node, 'Text')) && (unicode = unicode2latex_1.latex2unicode[`_{${arg}}`]))
899
900
  return this.text(unicode);
900
901
  if (arg = this.argument(node, 'Block'))
901
902
  return this.clean(arg);
@@ -923,7 +924,7 @@ class Parser {
923
924
  if (arg = this.argument(node, 'text')) {
924
925
  if (node.command === 'mbox' && !arg)
925
926
  return this.text('\u200b');
926
- unicode = unicode2latex_1.latex[`\\${node.command}{${arg}}`];
927
+ unicode = unicode2latex_1.latex2unicode[`\\${node.command}{${arg}}`];
927
928
  return this.text(unicode || (node.command === 'hspace' ? ' ' : arg));
928
929
  }
929
930
  else if (!node.arguments.required.length) {
@@ -978,7 +979,7 @@ class Parser {
978
979
  value: JSON.parse(JSON.stringify(this.newcommands[node.command])),
979
980
  });
980
981
  }
981
- if (unicode2latex_1.diacritics.tounicode[node.command]) {
982
+ if (unicode2latex_1.combining.tounicode[node.command]) {
982
983
  node.arguments.required = this.clean(node.arguments.required);
983
984
  let block;
984
985
  if (node.arguments.required.length === 1 && node.arguments.required[0].kind === 'Text') {
@@ -1023,15 +1024,15 @@ class Parser {
1023
1024
  return this.clean({
1024
1025
  kind: 'Block',
1025
1026
  markup: {},
1026
- value: [this.text(` ${unicode2latex_1.diacritics.tounicode[node.command]}`)].concat(node.arguments.required),
1027
+ value: [this.text(` ${unicode2latex_1.combining.tounicode[node.command]}`)].concat(node.arguments.required),
1027
1028
  });
1028
1029
  }
1029
1030
  }
1030
- if (unicode = unicode2latex_1.latex[node.source] || unicode2latex_1.latex[`${node.source}{}`])
1031
+ if (unicode = unicode2latex_1.latex2unicode[node.source] || unicode2latex_1.latex2unicode[`${node.source}{}`])
1031
1032
  return this.text(unicode);
1032
- if ((unicode = unicode2latex_1.latex[`\\${node.command}`] || unicode2latex_1.latex[`\\${node.command}{}`]) && this.argument(node, 'none'))
1033
+ if ((unicode = unicode2latex_1.latex2unicode[`\\${node.command}`] || unicode2latex_1.latex2unicode[`\\${node.command}{}`]) && this.argument(node, 'none'))
1033
1034
  return this.text(unicode);
1034
- if ((arg = this.argument(node, 'Text')) && (unicode = unicode2latex_1.latex[`\\${node.command}{${arg}}`]))
1035
+ if ((arg = this.argument(node, 'Text')) && (unicode = unicode2latex_1.latex2unicode[`\\${node.command}{${arg}}`]))
1035
1036
  return this.text(unicode);
1036
1037
  break;
1037
1038
  }
@@ -1324,7 +1325,7 @@ class Parser {
1324
1325
  }
1325
1326
  }
1326
1327
  else if (exports.fields.unabbrev.includes(field.name)) { // doesn't get sentence casing anyhow TODO: booktitle does!
1327
- this.entry.fields[this.field.name].push((this.options.unabbreviate[this.field.text] || this.field.text).normalize('NFC'));
1328
+ this.entry.fields[this.field.name].push(this.options.unabbreviate[this.field.text] || this.field.text);
1328
1329
  }
1329
1330
  else {
1330
1331
  if (this.field.preserveRanges) {
@@ -1357,7 +1358,7 @@ class Parser {
1357
1358
  }
1358
1359
  }
1359
1360
  }
1360
- this.entry.fields[this.field.name].push(this.convertToSentenceCase(this.field.text).normalize('NFC'));
1361
+ this.entry.fields[this.field.name].push(this.convertToSentenceCase(this.field.text));
1361
1362
  }
1362
1363
  }
1363
1364
  this.field = null;
@@ -1486,7 +1487,7 @@ class Parser {
1486
1487
  const cmd = mode === 'sup' ? '^' : '_';
1487
1488
  let script = '';
1488
1489
  for (const char of chars) {
1489
- const unicode = unicode2latex_1.latex[`${cmd}${char}`] || unicode2latex_1.latex[`${cmd}{${char}}`];
1490
+ const unicode = unicode2latex_1.latex2unicode[`${cmd}${char}`] || unicode2latex_1.latex2unicode[`${cmd}{${char}}`];
1490
1491
  script += unicode ? unicode : `<${mode}>${char}</${mode}>`;
1491
1492
  }
1492
1493
  script = script.replace(new RegExp(`</${mode}><${mode}>`, 'g'), '');
package/package.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "@retorquere/bibtex-parser",
3
- "version": "7.0.8",
3
+ "version": "7.0.9",
4
4
  "description": "BibTeX parser",
5
5
  "main": "index.js",
6
6
  "typings": "./index.d.ts",
@@ -11,7 +11,7 @@
11
11
  "tsc": "tsc -d",
12
12
  "poststart": "npm run docs",
13
13
  "pretest": "npm start",
14
- "test": "tap test/tap --no-timeout --no-coverage",
14
+ "test": "tap --timeout 0 --disable-coverage --allow-empty-coverage",
15
15
  "snap": "npm test --snapshot",
16
16
  "snap:big": "npm test --snapshot --big",
17
17
  "minitest": "peggy grammar.peggy && ./build/crossref.py && tsc -d && node i.js",
@@ -37,31 +37,31 @@
37
37
  "author": "Emiliano Heyns",
38
38
  "license": "ISC",
39
39
  "devDependencies": {
40
- "@microsoft/api-documenter": "^7.22.33",
41
- "@microsoft/api-extractor": "^7.36.4",
42
- "@types/node": "^20.4.9",
43
- "@typescript-eslint/eslint-plugin": "^6.3.0",
44
- "@typescript-eslint/parser": "^6.3.0",
40
+ "@microsoft/api-documenter": "^7.23.20",
41
+ "@microsoft/api-extractor": "^7.39.4",
42
+ "@types/node": "^20.11.9",
43
+ "@typescript-eslint/eslint-plugin": "^6.19.1",
44
+ "@typescript-eslint/parser": "^6.19.1",
45
45
  "command-line-args": "^5.2.1",
46
- "csv": "^6.3.1",
46
+ "csv": "^6.3.6",
47
47
  "digital-tree": "^2.0.4",
48
48
  "ejs": "^3.1.9",
49
- "eslint": "^8.46.0",
50
- "eslint-plugin-import": "^2.28.0",
49
+ "eslint": "^8.56.0",
50
+ "eslint-plugin-import": "^2.29.1",
51
51
  "eslint-plugin-prefer-arrow": "^1.2.3",
52
- "glob": "^10.3.3",
52
+ "glob": "^10.3.10",
53
53
  "mkdirp": "^3.0.1",
54
54
  "node-fetch": "^3.3.2",
55
55
  "peggy": "^3.0.2",
56
- "piscina": "^4.1.0",
56
+ "piscina": "^4.3.0",
57
57
  "slug": "^8.2.3",
58
- "tap": "^16.3.8",
59
- "ts-node": "^10.9.1",
60
- "tslib": "^2.6.1",
61
- "typescript": "^5.1.6"
58
+ "tap": "^18.7.0",
59
+ "ts-node": "^10.9.2",
60
+ "tslib": "^2.6.2",
61
+ "typescript": "^5.3.3"
62
62
  },
63
63
  "dependencies": {
64
- "unicode2latex": "^3.0.3",
64
+ "unicode2latex": "^4.0.42",
65
65
  "xregexp": "^5.1.1"
66
66
  },
67
67
  "files": [
package/sentence-case.js CHANGED
@@ -17,7 +17,7 @@ const re = {
17
17
  allCaps: new RegExp(`^[${Lu}${N}${No}]+$`),
18
18
  skipWords: /^(but|or|yet|so|for|and|nor|a|an|the|at|by|from|in|into|of|on|to|with|updown|as)$/i,
19
19
  // chemElements: /^(H|He|Li|Be|B|C|N|O|F|Ne|Na|Mg|Al|Si|P|S|Cl|Ar|K|Ca|Sc|Ti|V|Cr|Mn|Fe|Co|Ni|Cu|Zn|Ga|Ge|As|Se|Br|Kr|Rb|Sr|Y|Zr|Nb|Mo|Tc|Ru|Rh|Pb|Ag|Cd|In|Sn|Sb|Te|I|Xe|Cs|Ba|La|Hf|Ta|W|Re|Os|Ir|Pt|Au|Hg|Tl|Pb|Bi|Po|At|Rn|Fr|Ra|Ac|Rf|Db|Sg|Bh|Hs|Mt|Ds|Rg|Cn|Nh|Fl|Mc|Lv|Ts|Og|La|Ce|Pr|Nd|Pm|Sm|Eu|Gd|Tb|Dy|Ho|Er|Tm|Yb|Lu|Ac|Th|Pa|U|Np|Pu|Am|Cm|Bk|Cf|Es|Fm|Md|No|Lr)$/,
20
- words: new RegExp(`([\uFFFD${L}${N}${No}]+([\uFFFD${Pc}${L}${N}${No}]*))|(\\s([\uFFFD${Lu}]+[.]){2,})?`, 'g'),
20
+ words: new RegExp(`([\uFFFD${L}${N}${No}]+([\uFFFD${Pc}${L}${N}${No}]*))|(\\s([\uFFFD${Lu}]+[.]){2,})?`, 'g'), // compound words and acronyms
21
21
  titleCase: new RegExp(`^[${Lu}][${Ll}${N}${No}]+$`),
22
22
  // private aint = XRegExp("^\\p{L}n't(?=$|[\\P{L}])") // isn't
23
23
  // private word = XRegExp('^\\p{L}+([-.]\\p{L}+)*') // also match gallium-nitride as one word