bitaboom 1.0.0

package/dist/index.d.ts

@@ -0,0 +1,434 @@
+/**
+ * Removes extreme Arabic underscores (ـ) that appear at the beginning or end of a line or in text.
+ * Does not affect Hijri dates (e.g., 1424هـ) or specific Arabic terms.
+ * Example: "ـThis is a textـ" will be changed to "This is a text".
+ * @param {string} text - The input text to apply the rule to.
+ * @returns {string} - The modified text with extreme underscores removed.
+ */
+export const cleanExtremeArabicUnderscores: (text: string) => string;
+/**
+ * Converts Urdu symbols to their Arabic equivalents.
+ * Example: 'ھذا' will be changed to 'هذا', 'ی' to 'ي'.
+ * @param {string} text - The input text containing Urdu symbols.
+ * @returns {string} - The modified text with Urdu symbols converted to Arabic symbols.
+ */
+export const convertUrduSymbolsToArabic: (text: string) => string;
+/**
+ * Fixes the trailing "و" (wow) in phrases such as "عليكم و رحمة" to "عليكم ورحمة".
+ * This function attempts to correct phrases where "و" appears unnecessarily, particularly in greetings.
+ * Example: 'السلام عليكم و رحمة' will be changed to 'السلام عليكم ورحمة'.
+ * @param {string} text - The input text containing the "و" character.
+ * @returns {string} - The modified text with unnecessary trailing "و" characters corrected.
+ */
+export const fixTrailingWow: (text: string) => string;
+/**
+ * Inserts a space between Arabic text and numbers.
+ * Example: 'الآية37' will be changed to 'الآية 37'.
+ * @param {string} text - The input text containing Arabic text followed by numbers.
+ * @returns {string} - The modified text with spaces inserted between Arabic text and numbers.
+ */
+export const addSpaceBetweenArabicTextAndNumbers: (text: string) => string;
+/**
+ * Removes English letters and symbols from the text, including ampersands, slashes, and other symbols.
+ * Example: 'أحب & لنفسي' will be changed to 'أحب   لنفسي'.
+ * @param {string} text - The input text containing English letters and symbols.
+ * @returns {string} - The modified text with English letters and symbols removed.
+ */
+export const stripEnglishCharactersAndSymbols: (text: string) => string;
+/**
+ * Removes single-digit numbers surrounded by Arabic text. Also removes dashes (-) not followed by a number.
+ * For example, removes '3' from 'وهب 3 وقال' but does not remove '121' from 'لوحه 121 الجرح'.
+ * @param {string} text - The input text to apply the rule to.
+ * @returns {string} - The modified text with non-index numbers and dashes removed.
+ */
+export const removeNonIndexSignatures: (text: string) => string;
+/**
+ * Removes characters enclosed in square brackets [] or parentheses () if they are Arabic letters or Arabic-Indic numerals.
+ * Example: '[س]' or '(س)' will be removed.
+ * @param {string} text - The input text to apply the rule to.
+ * @returns {string} - The modified text with singular codes removed.
+ */
+export const removeSingularCodes: (text: string) => string;
+/**
+ * Removes solitary Arabic letters unless they are the 'ha' letter, which is used in Hijri years.
+ * Example: "ب ا الكلمات ت" will be changed to "ا الكلمات".
+ * @param {string} text - The input text to apply the rule to.
+ * @returns {string} - The modified text with solitary Arabic letters removed.
+ */
+export const removeSolitaryArabicLetters: (text: string) => string;
+/**
+ * Replaces the 'tah marbutah' (ة) character with 'ha' (ه).
+ * Example: 'مدرسة' will be changed to 'مدرسه'.
+ * @param {string} text - The input text to apply the rule to.
+ * @returns {string} - The modified text with 'ta marbutah' replaced by 'ha'.
+ */
+export const replaceTaMarbutahWithHa: (text: string) => string;
+/**
+ * Removes Arabic diacritics (tashkeel) and the tatweel (elongation) character.
+ * Example: 'مُحَمَّدٌ' will be changed to 'محمد'.
+ * @param {string} text - The input text to apply the rule to.
+ * @returns {string} - The modified text with diacritics and tatweel removed.
+ */
+export const stripDiacritics: (text: string) => string;
+/**
+ * Removes zero-width joiners (ZWJ) and other zero-width characters from the input text.
+ * Zero-width characters include U+200B to U+200F, U+202A to U+202E, U+2060 to U+2064, and U+FEFF.
+ * @param {string} text - The input text to apply the rule to.
+ * @returns {string} - The modified text with zero-width characters removed.
+ */
+export const stripZeroWidthCharacters: (text: string) => string;
+/**
+ * Replaces the 'alif maqsurah' (ى) character with the regular 'ya' (ي).
+ * Example: 'رؤيى' will be changed to 'رؤيي'.
+ * @param {string} text - The input text to apply the rule to.
+ * @returns {string} - The modified text with 'alif maqsurah' replaced by 'ya'.
+ */
+export const replaceAlifMaqsurah: (text: string) => string;
+/**
+ * Replaces English punctuation (question mark and semicolon) with their Arabic equivalents.
+ * Example: '?' will be replaced with '؟', and ';' with '؛'.
+ * @param {string} text - The input text to apply the rule to.
+ * @returns {string} - The modified text with English punctuation replaced by Arabic punctuation.
+ */
+export const replaceEnglishPunctuationWithArabic: (text: string) => string;
+/**
+ * Simplifies all forms of 'alif' (أ, إ, and آ) to the basic 'ا'.
+ * Example: 'أنا إلى الآفاق' will be changed to 'انا الى الافاق'.
+ * @param {string} text - The input text to apply the rule to.
+ * @returns {string} - The modified text with simplified 'alif' characters.
+ */
+export const normalizeAlifVariants: (text: string) => string;
+/**
+ * Adds line breaks after punctuation marks such as periods, exclamation points, and question marks.
+ * Example: 'Text.' becomes 'Text.\n'.
+ * @param {string} text - The input text containing punctuation.
+ * @returns {string} - The modified text with line breaks added after punctuation.
+ */
+export const insertLineBreaksAfterPunctuation: (text: string) => string;
+/**
+ * Adds spaces before and after punctuation, except for certain cases like quoted text or ayah references.
+ * Example: 'Text,word' becomes 'Text, word'.
+ * @param {string} text - The input text containing punctuation.
+ * @returns {string} - The modified text with spaces added before and after punctuation.
+ */
+export const addSpaceBeforeAndAfterPunctuation: (text: string) => string;
+/**
+ * Turns regular double quotes surrounding a body of text into smart quotes.
+ * Also fixes incorrect starting quotes by ensuring the string starts with an opening quote if needed.
+ * Example: 'The "quick brown" fox' becomes 'The “quick brown” fox'.
+ * @param {string} text - The input text to apply the rule to.
+ * @returns {string} - The modified text with smart quotes applied.
+ */
+export const applySmartQuotes: (text: string) => string;
+/**
+ * Replaces literal new line characters (\n) and carriage returns (\r) with actual line breaks.
+ * Example: 'A\\nB' becomes 'A\nB'.
+ * @param {string} text - The input text containing literal new lines.
+ * @returns {string} - The modified text with actual line breaks.
+ */
+export const cleanLiteralNewLines: (text: string) => string;
+/**
+ * Removes trailing spaces from each line in a multiline string.
+ * Example: " This is a line   \nAnother line   " becomes "This is a line\nAnother line".
+ * @param {string} text - The input text to apply the rule to.
+ * @returns {string} - The modified text with trailing spaces removed.
+ */
+export const cleanMultilines: (text: string) => string;
+/**
+ * Checks if the input string consists of only punctuation characters.
+ * @param {string} text - The input text to check.
+ * @returns {boolean} - Returns true if the string contains only punctuation, false otherwise.
+ */
+export const isOnlyPunctuation: (text: string) => boolean;
+export const cleanJunkFromText: (text: string) => string;
+/**
+ * Cleans unnecessary spaces before punctuation marks such as periods, commas, and question marks.
+ * Example: 'This is a sentence , with extra space .' becomes 'This is a sentence, with extra space.'.
+ * @param {string} text - The input text to apply the rule to.
+ * @returns {string} - The modified text with cleaned spaces before punctuation.
+ */
+export const cleanSpacesBeforePeriod: (text: string) => string;
+/**
+ * Condenses multiple asterisks (*) into a single one.
+ * Example: '***' becomes '*'.
+ * @param {string} text - The input text to apply the rule to.
+ * @returns {string} - The modified text with condensed asterisks.
+ */
+export const condenseAsterisks: (text: string) => string;
+/**
+ * Replaces occurrences of colons surrounded by periods (e.g., '.:.' or ':') with a single colon.
+ * Example: 'This.:. is a test' becomes 'This: is a test'.
+ * @param {string} text - The input text to apply the rule to.
+ * @returns {string} - The modified text with condensed colons.
+ */
+export const condenseColons: (text: string) => string;
+/**
+ * Condenses two or more dashes (--) into a single dash (-).
+ * Example: 'This is some ---- text' becomes 'This is some - text'.
+ * @param {string} text - The input text to apply the rule to.
+ * @returns {string} - The modified text with condensed dashes.
+ */
+export const condenseDashes: (text: string) => string;
+/**
+ * Replaces sequences of two or more periods (e.g., '...') with an ellipsis character (…).
+ * Example: 'This is a test...' becomes 'This is a test…'.
+ * @param {string} text - The input text to apply the rule to.
+ * @returns {string} - The modified text with ellipses condensed.
+ */
+export const condenseEllipsis: (text: string) => string;
+/**
+ * Reduces multiple consecutive line breaks (3 or more) to exactly 2 line breaks.
+ * Example: 'This is line 1\n\n\n\nThis is line 2' becomes 'This is line 1\n\nThis is line 2'.
+ * @param {string} text - The input text to apply the rule to.
+ * @returns {string} - The modified text with condensed line breaks.
+ */
+export const reduceMultilineBreaksToDouble: (text: string) => string;
+/**
+ * Reduces multiple consecutive line breaks (2 or more) to exactly 1 line break.
+ * Example: 'This is line 1\n\nThis is line 2' becomes 'This is line 1\nThis is line 2'.
+ * @param {string} text - The input text to apply the rule to.
+ * @returns {string} - The modified text with condensed line breaks.
+ */
+export const reduceMultilineBreaksToSingle: (text: string) => string;
+/**
+ * Condenses multiple periods separated by spaces (e.g., '. . .') into a single period.
+ * Example: 'This . . . is a test' becomes 'This. is a test'.
+ * @param {string} text - The input text to apply the rule to.
+ * @returns {string} - The modified text with condensed periods.
+ */
+export const condensePeriods: (text: string) => string;
+/**
+ * Condenses multiple underscores (__) or Arabic Tatweel characters (ـــــ) into a single underscore or Tatweel.
+ * Example: 'This is ـــ some text __' becomes 'This is ـ some text _'.
+ * @param {string} text - The input text to apply the rule to.
+ * @returns {string} - The modified text with condensed underscores.
+ */
+export const condenseUnderscores: (text: string) => string;
+/**
+ * Replaces double parentheses or brackets with single ones.
+ * Example: '((text))' becomes '(text)'.
+ * @param {string} text - The input text to apply the rule to.
+ * @returns {string} - The modified text with condensed brackets.
+ */
+export const doubleToSingleBrackets: (text: string) => string;
+/**
+ * Formats a multiline string by joining sentences and maintaining footnotes on their own lines.
+ * Footnotes are identified by Arabic and English numerals.
+ * Example: 'Sentence one.\n(1) A footnote.\nSentence two.' remains the same, while regular sentences are joined.
+ * @param {string} input - The input text containing sentences and footnotes.
+ * @returns {string} - The formatted text.
+ */
+export const formatStringBySentence: (input: string) => string;
+/**
+ * Removes unnecessary spaces around slashes in references.
+ * Example: '127 / 11' becomes '127/11'.
+ * @param {string} text - The input text containing references.
+ * @returns {string} - The modified text with spaces removed around slashes.
+ */
+export const normalizeSlashInReferences: (text: string) => string;
+/**
+ * Reduces multiple spaces or tabs to a single space.
+ * Example: 'This   is a   text' becomes 'This is a text'.
+ * @param {string} text - The input text containing extra spaces.
+ * @returns {string} - The modified text with reduced spaces.
+ */
+export const normalizeSpaces: (text: string) => string;
+/**
+ * Removes spaces inside brackets, parentheses, or square brackets.
+ * Example: '( a b )' becomes '(a b)'.
+ * @param {string} text - The input text with spaces inside brackets.
+ * @returns {string} - The modified text with spaces removed inside brackets.
+ */
+export const removeSpaceInsideBrackets: (text: string) => string;
+/**
+ * Removes bold styling from text by normalizing the string and removing stylistic characters.
+ * @param {string} text - The input text containing bold characters.
+ * @returns {string} - The modified text with bold styling removed.
+ */
+export const stripBoldStyling: (text: string) => string;
+/**
+ * Removes italicized characters by replacing italic Unicode characters with their normal counterparts.
+ * Example: '𝘼𝘽𝘾' becomes 'ABC'.
+ * @param {string} text - The input text containing italicized characters.
+ * @returns {string} - The modified text with italics removed.
+ */
+export const stripItalicsStyling: (text: string) => string;
+/**
+ * Removes all bold and italic styling from the input text.
+ * @param {string} text - The input text to remove styling from.
+ * @returns {string} - The modified text with all styling removed.
+ */
+export const stripStyling: (text: string) => string;
+/**
+ * Removes unnecessary spaces inside quotes.
+ * Example: '“ Text ”' becomes '“Text”'.
+ * @param {string} text - The input text with spaces inside quotes.
+ * @returns {string} - The modified text with spaces removed inside quotes.
+ */
+export const trimSpaceInsideQuotes: (text: string) => string;
+/**
+ * Converts a string that resembles JSON but with numeric keys and single-quoted values
+ * into valid JSON format. This function replaces numeric keys with quoted numeric keys
+ * and ensures all values are double-quoted as required by JSON.
+ *
+ * @param {string} str - The input string that needs to be fixed into valid JSON.
+ * @returns {string} - A valid JSON string.
+ *
+ * @example
+ * const result = normalizeJsonSyntax("{10: 'abc', 20: 'def'}");
+ * console.log(result); // '{"10": "abc", "20": "def"}'
+ */
+export const normalizeJsonSyntax: (str: string) => string;
+/**
+ * Checks if a given string resembles a JSON object with numeric or quoted keys and values
+ * that are single or double quoted. This is useful for detecting malformed JSON-like
+ * structures that can be fixed by the `normalizeJsonSyntax` function.
+ *
+ * @param {string} str - The input string to check.
+ * @returns {boolean} - Returns true if the string is JSON-like, false otherwise.
+ *
+ * @example
+ * const result = isJsonStructureValid("{10: 'abc', 'key': 'value'}");
+ * console.log(result); // true
+ */
+export const isJsonStructureValid: (str: string) => boolean;
+/**
+ * Splits a string by spaces and quoted substrings.
+ *
+ * This function takes an input string and splits it into parts where substrings
+ * enclosed in double quotes are treated as a single part. Other substrings
+ * separated by spaces are split normally.
+ *
+ * @param {string} query - The input string to be split.
+ * @returns {string[]} An array of strings, with quoted substrings kept intact.
+ *
+ * @example
+ * const result = splitByQuotes('"This is" "a part of the" "string and"');
+ * console.log(result); // ["This is", "a part of the", "string and"]
+ */
+export const splitByQuotes: (query: string) => string[];
+/**
+ * Removes various symbols, part references, and numerical markers from the text.
+ * Example: '(1) (2/3)' becomes ''.
+ * @param {string} text - The input text to apply the rule to.
+ * @returns {string} - The modified text with symbols and part references removed.
+ */
+export const cleanSymbolsAndPartReferences: (text: string) => string;
+/**
+ * Removes trailing page numbers formatted as '-[46]-' from the text.
+ * Example: 'This is some -[46]- text' becomes 'This is some text'.
+ * @param {string} text - The input text with trailing page numbers.
+ * @returns {string} - The modified text with page numbers removed.
+ */
+export const cleanTrailingPageNumbers: (text: string) => string;
+/**
+ * Replaces consecutive line breaks and whitespace characters with a single space.
+ * Example: 'a\nb' becomes 'a b'.
+ * @param {string} text - The input text containing line breaks or multiple spaces.
+ * @returns {string} - The modified text with spaces.
+ */
+export const replaceLineBreaksWithSpaces: (text: string) => string;
+/**
+ * Removes all numeric digits from the text.
+ * Example: 'abc123' becomes 'abc'.
+ * @param {string} text - The input text containing digits.
+ * @returns {string} - The modified text with digits removed.
+ */
+export const stripAllDigits: (text: string) => string;
+/**
+ * Removes death year references like "(d. 390H)" and "[d. 100h]" from the text.
+ * Example: 'Sufyān ibn ‘Uyaynah (d. 198h)' becomes 'Sufyān ibn ‘Uyaynah'.
+ * @param {string} text - The input text containing death year references.
+ * @returns {string} - The modified text with death years removed.
+ */
+export const removeDeathYear: (text: string) => string;
+/**
+ * Removes numeric digits and dashes from the text.
+ * Example: 'ABC 123-Xyz' becomes 'ABC Xyz'.
+ * @param {string} text - The input text containing digits and dashes.
+ * @returns {string} - The modified text with numbers and dashes removed.
+ */
+export const removeNumbersAndDashes: (text: string) => string;
+/**
+ * Removes single digit references like (1), «2», [3] from the text.
+ * Example: 'Ref (1), Ref «2», Ref [3]' becomes 'Ref , Ref , Ref '.
+ * @param {string} text - The input text containing single digit references.
+ * @returns {string} - The modified text with single digit references removed.
+ */
+export const removeSingleDigitReferences: (text: string) => string;
+/**
+ * Removes URLs from the text.
+ * Example: 'Visit https://example.com' becomes 'Visit '.
+ * @param {string} text - The input text containing URLs.
+ * @returns {string} - The modified text with URLs removed.
+ */
+export const removeUrls: (text: string) => string;
+/**
+ * Replaces common Arabic prefixes (like 'Al-', 'Ar-', 'Ash-', etc.) with 'al-' in the text.
+ * Handles different variations of prefixes such as Ash- and Al- but not when the second word
+ * does not start with 'S'.
+ * Example: 'Ash-Shafiee' becomes 'al-Shafiee'.
+ *
+ * @param {string} text - The input text containing Arabic prefixes.
+ * @returns {string} - The modified text with standardized 'al-' prefixes.
+ */
+export const normalizeArabicPrefixesToAl: (text: string) => string;
+/**
+ * Removes double occurrences of Arabic apostrophes such as ʿʿ or ʾʾ in the text.
+ * Example: 'ʿulamāʾʾ' becomes 'ʿulamāʾ'.
+ *
+ * @param {string} text - The input text containing double apostrophes.
+ * @returns {string} - The modified text with condensed apostrophes.
+ */
+export const normalizeDoubleApostrophes: (text: string) => string;
+/**
+ * Replaces common salutations such as "sallahu alayhi wasallam" with "ﷺ" in the text.
+ * It also handles variations of the salutation phrase, including 'peace and blessings be upon him'.
+ * Example: 'Then Muḥammad (sallahu alayhi wasallam)' becomes 'Then Muḥammad ﷺ'.
+ *
+ * @param {string} text - The input text containing salutations.
+ * @returns {string} - The modified text with salutations replaced.
+ */
+export const replaceSalutationsWithSymbol: (text: string) => string;
+/**
+ * Normalizes the text by removing diacritics, apostrophes, and dashes.
+ * Example: 'Al-Jadwal' becomes 'AlJadwal'.
+ *
+ * @param {string} input - The input text to normalize.
+ * @returns {string} - The normalized text.
+ */
+export const normalize: (input: string) => string;
+/**
+ * Replaces various apostrophe characters (‛, ’, ‘) with the standard apostrophe (').
+ * Example: '‛ulama’ al-su‘' becomes ''ulama' al-su''.
+ *
+ * @param {string} text - The input text containing different apostrophe characters.
+ * @returns {string} - The modified text with normalized apostrophes.
+ */
+export const normalizeApostrophes: (text: string) => string;
+/**
+ * Strips common Arabic prefixes like 'al-', 'bi-', 'fī', 'wa-', etc. from the beginning of words.
+ * Example: 'al-Bukhari' becomes 'Bukhari'.
+ *
+ * @param {string} text - The input text containing Arabic prefixes.
+ * @returns {string} - The modified text with prefixes stripped.
+ */
+export const removeArabicPrefixes: (text: string) => string;
+/**
+ * Simplifies English transliterations by removing diacritics, apostrophes, and common prefixes.
+ * Example: 'Al-Jadwal' becomes 'Jadwal', and 'āḍġḥīṣṭū' becomes 'adghistu'.
+ *
+ * @param {string} text - The input text to simplify.
+ * @returns {string} - The simplified text.
+ */
+export const normalizeTransliteratedEnglish: (text: string) => string;
+/**
+ * Extracts the initials from the input string, typically used for names or titles.
+ * Example: 'Nayl al-Awtar' becomes 'NA'.
+ *
+ * @param {string} text - The input text to extract initials from.
+ * @returns {string} - The extracted initials.
+ */
+export const extractInitials: (fullName: string) => string;
+
+//# sourceMappingURL=index.d.ts.map