@retorquere/bibtex-parser 6.4.14 → 6.4.17

package/index.d.ts

@@ -2,7 +2,7 @@ import * as bibtex from './grammar';
 import * as chunker from './chunker';
 import * as jabref from './jabref';
 import { JabRefMetadata } from './jabref';
-export declare function toSentenceCase(text: string, ignoreHTML?: boolean): string;
+export { toSentenceCase } from './sentence-case';
 type Node = bibtex.Bibliography | bibtex.Math | bibtex.Environment | bibtex.Block | bibtex.RegularCommand | bibtex.DiacriticCommand | bibtex.Entry | bibtex.Field | bibtex.NumberValue | bibtex.StringDeclaration | bibtex.StringReference | bibtex.SubscriptCommand | bibtex.SuperscriptCommand | bibtex.SymbolCommand | bibtex.TextValue | bibtex.PreambleExpression | bibtex.BracedComment | bibtex.LineComment | bibtex.Markup | bibtex.NonEntryText;
 export interface Name {
     /**

package/index.js

@@ -37,103 +37,9 @@ const jabref_1 = require("./jabref");
 const unicode2latex_1 = require("unicode2latex");
 const crossref_json_1 = __importDefault(require("./crossref.json"));
 const fields_json_1 = __importDefault(require("./fields.json"));
-const xregexp_1 = __importDefault(require("xregexp"));
-function restore(text, orig, preserve) {
-    for (const { start, end } of preserve) {
-        text = text.substring(0, start) + orig.substring(start, end) + text.substring(end);
-    }
-    return text;
-}
-class SentenceCaser {
-    constructor() {
-        this.acronym = (0, xregexp_1.default)('^(\\p{Lu}[.])+(?=$|[\\P{L}])');
-        this.quoted = (0, xregexp_1.default)('^"[^"]+"(?=$|[\\P{L}])');
-        this.innerCaps = (0, xregexp_1.default)('\\p{Ll}\\p{Lu}');
-        this.allCaps = (0, xregexp_1.default)('^\\p{Lu}+$');
-        this.aint = (0, xregexp_1.default)("^\\p{L}n't(?=$|[\\P{L}])"); // isn't
-        this.word = (0, xregexp_1.default)('^\\p{L}+(-\\p{L}+)*'); // also match gallium-nitride as one word
-        this.and = (0, xregexp_1.default)('^\\p{Lu}&\\p{Lu}(?=$|[\\P{L}])'); // Q&A
-    }
-    convert(text, ignoreHTML = false) {
-        this.input = text;
-        this.result = '';
-        this.sentenceStart = true;
-        const preserve = [];
-        if (ignoreHTML) {
-            let replace = true;
-            while (replace) {
-                replace = false;
-                // always keep the leading char, but skip markup
-                this.input = this.input.replace(/[^<>]<[^>]+>/, (match, i) => {
-                    preserve.push({ start: i + 1, end: i + match.length });
-                    replace = true;
-                    return match[0].repeat(match.length);
-                });
-            }
-            replace = true;
-            while (replace) {
-                replace = false;
-                // always keep the leading char, but skip markup
-                this.input = this.input.replace(/<[^>]+>[^<>]/, (match, i) => {
-                    preserve.push({ start: i, end: i + match.length - 1 });
-                    replace = true;
-                    return match[match.length - 1].repeat(match.length);
-                });
-            }
-        }
-        this.input = this.input.replace(/[;:]\s+A\s/g, match => match.toLowerCase());
-        this.input = this.input.replace(/[–—]\s*A\s/g, match => match.toLowerCase());
-        let m;
-        while (this.input) {
-            if (m = xregexp_1.default.exec(this.input, this.quoted)) { // "Hello There"
-                this.add(m[0], undefined, true);
-            }
-            else if (m = xregexp_1.default.exec(this.input, this.acronym)) { // U.S.
-                this.add(m[0], undefined, true);
-            }
-            else if (m = xregexp_1.default.exec(this.input, this.aint)) { // isn't
-                this.add(m[0], undefined, false);
-            }
-            else if (m = xregexp_1.default.exec(this.input, this.word)) {
-                this.add(m[0], '-', false);
-            }
-            else if (m = xregexp_1.default.exec(this.input, this.and)) {
-                this.add(m[0], undefined, true);
-            }
-            else {
-                this.add(this.input[0], undefined, false);
-            }
-        }
-        return restore(this.result, text, preserve);
-    }
-    add(word, splitter, keep) {
-        if (splitter) {
-            word = word.split(splitter).map((part, i) => {
-                if ((keep || this.sentenceStart) && i === 0)
-                    return part;
-                if (xregexp_1.default.exec(part, this.innerCaps))
-                    return part;
-                if (xregexp_1.default.exec(part, this.allCaps))
-                    return part;
-                return part.toLowerCase();
-            }).join(splitter);
-        }
-        else {
-            if (!keep)
-                word = word.toLowerCase();
-        }
-        this.result += word;
-        this.input = this.input.substr(word.length);
-        if (!word.match(/^\s+$/)) {
-            this.sentenceStart = !!word.match(/^[.?!]$/) || (word.length === 2 && word[1] === '.'); // Vitamin A. Vitamin B.
-        }
-    }
-}
-const sentenceCaser = new SentenceCaser;
-function toSentenceCase(text, ignoreHTML = false) {
-    return sentenceCaser.convert(text, ignoreHTML);
-}
-exports.toSentenceCase = toSentenceCase;
+var sentence_case_1 = require("./sentence-case");
+Object.defineProperty(exports, "toSentenceCase", { enumerable: true, get: function () { return sentence_case_1.toSentenceCase; } });
+const sentence_case_2 = require("./sentence-case");
 class ParserError extends Error {
     constructor(message, node) {
         super(message); // 'Error' breaks prototype chain here
@@ -1451,7 +1357,7 @@ class Parser {
     convertToSentenceCase(text) {
         if (!this.field.preserveRanges)
             return text;
-        const sentenceCased = restore(sentenceCaser.convert(text, true), text, this.field.preserveRanges);
+        const sentenceCased = (0, sentence_case_2.restore)((0, sentence_case_2.toSentenceCase)(text, true), text, this.field.preserveRanges);
         if (text !== sentenceCased)
             this.entry.sentenceCased = true;
         return sentenceCased;

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@retorquere/bibtex-parser",
-  "version": "6.4.14",
+  "version": "6.4.17",
   "description": "BibTeX parser",
   "main": "index.js",
   "typings": "./index.d.ts",
@@ -36,28 +36,28 @@
   "author": "Emiliano Heyns",
   "license": "ISC",
   "devDependencies": {
-    "@microsoft/api-documenter": "^7.22.3",
-    "@microsoft/api-extractor": "^7.34.7",
-    "@types/node": "^18.16.3",
-    "@typescript-eslint/eslint-plugin": "^5.59.2",
-    "@typescript-eslint/parser": "^5.59.2",
+    "@microsoft/api-documenter": "^7.22.32",
+    "@microsoft/api-extractor": "^7.36.3",
+    "@types/node": "^20.4.8",
+    "@typescript-eslint/eslint-plugin": "^6.2.1",
+    "@typescript-eslint/parser": "^6.2.1",
     "command-line-args": "^5.2.1",
-    "csv": "^6.2.11",
+    "csv": "^6.3.1",
     "digital-tree": "^2.0.4",
     "ejs": "^3.1.9",
-    "eslint": "^8.39.0",
-    "eslint-plugin-import": "^2.27.5",
+    "eslint": "^8.46.0",
+    "eslint-plugin-import": "^2.28.0",
     "eslint-plugin-prefer-arrow": "^1.2.3",
-    "glob": "^10.2.2",
+    "glob": "^10.3.3",
     "mkdirp": "^3.0.1",
-    "node-fetch": "^3.3.1",
+    "node-fetch": "^3.3.2",
     "peggy": "^3.0.2",
-    "piscina": "^3.2.0",
-    "slug": "^8.2.2",
-    "tap": "^16.3.4",
+    "piscina": "^4.1.0",
+    "slug": "^8.2.3",
+    "tap": "^16.3.8",
     "ts-node": "^10.9.1",
-    "tslib": "^2.5.0",
-    "typescript": "^5.0.4"
+    "tslib": "^2.6.1",
+    "typescript": "^5.1.6"
   },
   "dependencies": {
     "unicode2latex": "^3.0.3",