@stll/anonymize 0.0.7 → 0.0.9

package/dist/index.js

@@ -1,6 +1,5 @@
 import { at, be, bg, cy, cz, de, dk, ee, es, fi, fr, gb, gr, hr, hu, ie, it, lt, lu, lv, mt, nl, pl, pt, ro, se, si, sk } from "@stll/stdnum";
 import { toRegex } from "@stll/stdnum/patterns";
-import charGroupsJson from "@stll/anonymize-data/config/char-groups.json";
 import { TextSearch } from "@stll/text-search";
 //#region src/types.ts
 /**
@@ -995,11 +994,513 @@ const POST_NOMINALS = [
 	"CIPP"
 ];
 //#endregion
+//#region src/util/char-groups-data.json
+var char_groups_data_default = {
+	_comment: "Unicode character equivalence groups. Used to build regex character classes that match all variants of a character type.",
+	groups: {
+		"dash": {
+			"description": "Dash-like characters (hyphens, en-dash, em-dash, minus)",
+			"chars": [
+				{
+					"char": "-",
+					"name": "hyphen-minus",
+					"code": "U+002D"
+				},
+				{
+					"char": "–",
+					"name": "en-dash",
+					"code": "U+2013"
+				},
+				{
+					"char": "—",
+					"name": "em-dash",
+					"code": "U+2014"
+				},
+				{
+					"char": "‐",
+					"name": "hyphen",
+					"code": "U+2010"
+				},
+				{
+					"char": "‑",
+					"name": "non-breaking hyphen",
+					"code": "U+2011"
+				},
+				{
+					"char": "−",
+					"name": "minus sign",
+					"code": "U+2212"
+				},
+				{
+					"char": "⁃",
+					"name": "hyphen bullet",
+					"code": "U+2043"
+				},
+				{
+					"char": "‒",
+					"name": "figure dash",
+					"code": "U+2012"
+				},
+				{
+					"char": "―",
+					"name": "horizontal bar",
+					"code": "U+2015"
+				},
+				{
+					"char": "⸺",
+					"name": "two-em dash",
+					"code": "U+2E3A"
+				},
+				{
+					"char": "⸻",
+					"name": "three-em dash",
+					"code": "U+2E3B"
+				},
+				{
+					"char": "־",
+					"name": "Hebrew maqaf",
+					"code": "U+05BE"
+				}
+			]
+		},
+		"space": {
+			"description": "Space-like characters",
+			"chars": [
+				{
+					"char": " ",
+					"name": "space",
+					"code": "U+0020"
+				},
+				{
+					"char": "\xA0",
+					"name": "no-break space",
+					"code": "U+00A0"
+				},
+				{
+					"char": " ",
+					"name": "en space",
+					"code": "U+2002"
+				},
+				{
+					"char": " ",
+					"name": "em space",
+					"code": "U+2003"
+				},
+				{
+					"char": " ",
+					"name": "thin space",
+					"code": "U+2009"
+				},
+				{
+					"char": " ",
+					"name": "hair space",
+					"code": "U+200A"
+				},
+				{
+					"char": " ",
+					"name": "narrow no-break space",
+					"code": "U+202F"
+				},
+				{
+					"char": " ",
+					"name": "Ogham space mark",
+					"code": "U+1680"
+				},
+				{
+					"char": " ",
+					"name": "en quad",
+					"code": "U+2000"
+				},
+				{
+					"char": " ",
+					"name": "em quad",
+					"code": "U+2001"
+				},
+				{
+					"char": " ",
+					"name": "three-per-em space",
+					"code": "U+2004"
+				},
+				{
+					"char": " ",
+					"name": "four-per-em space",
+					"code": "U+2005"
+				},
+				{
+					"char": " ",
+					"name": "six-per-em space",
+					"code": "U+2006"
+				},
+				{
+					"char": " ",
+					"name": "figure space",
+					"code": "U+2007"
+				},
+				{
+					"char": " ",
+					"name": "punctuation space",
+					"code": "U+2008"
+				},
+				{
+					"char": " ",
+					"name": "medium mathematical space",
+					"code": "U+205F"
+				},
+				{
+					"char": "　",
+					"name": "ideographic space",
+					"code": "U+3000"
+				},
+				{
+					"char": "​",
+					"name": "zero width space",
+					"code": "U+200B"
+				}
+			]
+		},
+		"quote-double": {
+			"description": "Double quotation marks",
+			"chars": [
+				{
+					"char": "\"",
+					"name": "quotation mark",
+					"code": "U+0022"
+				},
+				{
+					"char": "“",
+					"name": "left double quotation mark",
+					"code": "U+201C"
+				},
+				{
+					"char": "”",
+					"name": "right double quotation mark",
+					"code": "U+201D"
+				},
+				{
+					"char": "„",
+					"name": "double low-9 quotation mark",
+					"code": "U+201E"
+				},
+				{
+					"char": "«",
+					"name": "left guillemet",
+					"code": "U+00AB"
+				},
+				{
+					"char": "»",
+					"name": "right guillemet",
+					"code": "U+00BB"
+				}
+			]
+		},
+		"quote-single": {
+			"description": "Single quotation marks and apostrophes",
+			"chars": [
+				{
+					"char": "'",
+					"name": "apostrophe",
+					"code": "U+0027"
+				},
+				{
+					"char": "‘",
+					"name": "left single quotation mark",
+					"code": "U+2018"
+				},
+				{
+					"char": "’",
+					"name": "right single quotation mark",
+					"code": "U+2019"
+				},
+				{
+					"char": "‚",
+					"name": "single low-9 quotation mark",
+					"code": "U+201A"
+				},
+				{
+					"char": "‹",
+					"name": "left single guillemet",
+					"code": "U+2039"
+				},
+				{
+					"char": "›",
+					"name": "right single guillemet",
+					"code": "U+203A"
+				},
+				{
+					"char": "ʼ",
+					"name": "modifier letter apostrophe",
+					"code": "U+02BC"
+				},
+				{
+					"char": "´",
+					"name": "acute accent",
+					"code": "U+00B4"
+				},
+				{
+					"char": "`",
+					"name": "grave accent",
+					"code": "U+0060"
+				},
+				{
+					"char": "ʽ",
+					"name": "modifier letter reversed comma",
+					"code": "U+02BD"
+				},
+				{
+					"char": "ʾ",
+					"name": "modifier letter right half ring",
+					"code": "U+02BE"
+				},
+				{
+					"char": "ʿ",
+					"name": "modifier letter left half ring",
+					"code": "U+02BF"
+				},
+				{
+					"char": "ˈ",
+					"name": "modifier letter vertical line",
+					"code": "U+02C8"
+				}
+			]
+		},
+		"dot": {
+			"description": "Dot-like characters",
+			"chars": [
+				{
+					"char": ".",
+					"name": "full stop",
+					"code": "U+002E"
+				},
+				{
+					"char": "·",
+					"name": "middle dot",
+					"code": "U+00B7"
+				},
+				{
+					"char": "•",
+					"name": "bullet",
+					"code": "U+2022"
+				},
+				{
+					"char": "․",
+					"name": "one dot leader",
+					"code": "U+2024"
+				},
+				{
+					"char": "。",
+					"name": "CJK full stop",
+					"code": "U+3002"
+				},
+				{
+					"char": "׃",
+					"name": "Hebrew sof pasuq",
+					"code": "U+05C3"
+				}
+			]
+		},
+		"slash": {
+			"description": "Slash-like characters",
+			"chars": [
+				{
+					"char": "/",
+					"name": "solidus",
+					"code": "U+002F"
+				},
+				{
+					"char": "⁄",
+					"name": "fraction slash",
+					"code": "U+2044"
+				},
+				{
+					"char": "∕",
+					"name": "division slash",
+					"code": "U+2215"
+				}
+			]
+		},
+		"colon": {
+			"description": "Colon-like characters",
+			"chars": [
+				{
+					"char": ":",
+					"name": "colon",
+					"code": "U+003A"
+				},
+				{
+					"char": "꞉",
+					"name": "modifier letter colon",
+					"code": "U+A789"
+				},
+				{
+					"char": "∶",
+					"name": "ratio",
+					"code": "U+2236"
+				},
+				{
+					"char": "：",
+					"name": "full-width colon",
+					"code": "U+FF1A"
+				},
+				{
+					"char": "፥",
+					"name": "Ethiopic colon",
+					"code": "U+1365"
+				}
+			]
+		},
+		"comma": {
+			"description": "Comma-like characters",
+			"chars": [
+				{
+					"char": ",",
+					"name": "comma",
+					"code": "U+002C"
+				},
+				{
+					"char": "‚",
+					"name": "single low-9 quotation mark (used as comma)",
+					"code": "U+201A"
+				},
+				{
+					"char": "،",
+					"name": "Arabic comma",
+					"code": "U+060C"
+				},
+				{
+					"char": "、",
+					"name": "ideographic comma",
+					"code": "U+3001"
+				},
+				{
+					"char": "，",
+					"name": "full-width comma",
+					"code": "U+FF0C"
+				},
+				{
+					"char": "﹐",
+					"name": "small comma",
+					"code": "U+FE50"
+				},
+				{
+					"char": "՝",
+					"name": "Armenian comma",
+					"code": "U+055D"
+				}
+			]
+		},
+		"ellipsis": {
+			"description": "Ellipsis characters",
+			"chars": [{
+				"char": "…",
+				"name": "horizontal ellipsis",
+				"code": "U+2026"
+			}]
+		},
+		"question-mark": {
+			"description": "Question mark variants",
+			"chars": [
+				{
+					"char": "?",
+					"name": "question mark",
+					"code": "U+003F"
+				},
+				{
+					"char": "？",
+					"name": "full-width question mark",
+					"code": "U+FF1F"
+				},
+				{
+					"char": "⁇",
+					"name": "double question mark",
+					"code": "U+2047"
+				},
+				{
+					"char": "⁈",
+					"name": "question exclamation mark",
+					"code": "U+2048"
+				},
+				{
+					"char": "؟",
+					"name": "Arabic question mark",
+					"code": "U+061F"
+				},
+				{
+					"char": "‽",
+					"name": "interrobang",
+					"code": "U+203D"
+				}
+			]
+		},
+		"exclamation-mark": {
+			"description": "Exclamation mark variants",
+			"chars": [
+				{
+					"char": "!",
+					"name": "exclamation mark",
+					"code": "U+0021"
+				},
+				{
+					"char": "！",
+					"name": "full-width exclamation mark",
+					"code": "U+FF01"
+				},
+				{
+					"char": "‼",
+					"name": "double exclamation mark",
+					"code": "U+203C"
+				},
+				{
+					"char": "¡",
+					"name": "inverted exclamation mark",
+					"code": "U+00A1"
+				}
+			]
+		},
+		"semicolon": {
+			"description": "Semicolon variants",
+			"chars": [
+				{
+					"char": ";",
+					"name": "semicolon",
+					"code": "U+003B"
+				},
+				{
+					"char": "؛",
+					"name": "Arabic semicolon",
+					"code": "U+061B"
+				},
+				{
+					"char": "；",
+					"name": "full-width semicolon",
+					"code": "U+FF1B"
+				},
+				{
+					"char": "፤",
+					"name": "Ethiopic semicolon",
+					"code": "U+1364"
+				}
+			]
+		},
+		"underscore": {
+			"description": "Underscore variants",
+			"chars": [{
+				"char": "_",
+				"name": "low line",
+				"code": "U+005F"
+			}, {
+				"char": "＿",
+				"name": "full-width low line",
+				"code": "U+FF3F"
+			}]
+		}
+	}
+};
+//#endregion
 //#region src/util/char-groups.ts
 /** Chars that need escaping inside a regex char class. */
 const REGEX_CLASS_SPECIAL = /[\\\]^-]/;
 const escapeForCharClass = (ch) => REGEX_CLASS_SPECIAL.test(ch) ? `\\${ch}` : ch;
-const loadConfig = () => charGroupsJson;
+const loadConfig = () => char_groups_data_default;
 /**
 * Get the raw characters for a named group.
 * Throws if the group does not exist.