backend v4 half

This commit is contained in:
2025-07-18 09:20:40 +02:00
parent aba7a506ad
commit 725516ad6c
4183 changed files with 217684 additions and 75056 deletions
@@ -0,0 +1,107 @@
// https://medium.com/dsinjs/implementing-lru-cache-in-javascript-94ba6755cda9
class Node {
constructor(key, value, next = null, prev = null) {
this.key = key;
this.value = value;
this.next = next;
this.prev = prev;
}
}
export default class LRUCache {
//set default limit of 10 if limit is not passed.
constructor(limit = 10) {
this.size = 0;
this.limit = limit;
this.head = null;
this.tail = null;
this.cache = {};
}
// Write Node to head of LinkedList
// update cache with Node key and Node reference
put(key, value){
this.ensureLimit();
if(!this.head){
this.head = this.tail = new Node(key, value);
}else{
const node = new Node(key, value, this.head);
this.head.prev = node;
this.head = node;
}
//Update the cache map
this.cache[key] = this.head;
this.size++;
}
// Read from cache map and make that node as new Head of LinkedList
get(key){
if(this.cache[key]){
const value = this.cache[key].value;
// node removed from it's position and cache
this.remove(key)
// write node again to the head of LinkedList to make it most recently used
this.put(key, value);
return value;
}
console.log(`Item not available in cache for key ${key}`);
}
ensureLimit(){
if(this.size === this.limit){
this.remove(this.tail.key)
}
}
remove(key){
const node = this.cache[key];
if(node.prev !== null){
node.prev.next = node.next;
}else{
this.head = node.next;
}
if(node.next !== null){
node.next.prev = node.prev;
}else{
this.tail = node.prev
}
delete this.cache[key];
this.size--;
}
clear() {
this.head = null;
this.tail = null;
this.size = 0;
this.cache = {};
}
// // Invokes the callback function with every node of the chain and the index of the node.
// forEach(fn) {
// let node = this.head;
// let counter = 0;
// while (node) {
// fn(node, counter);
// node = node.next;
// counter++;
// }
// }
// // To iterate over LRU with a 'for...of' loop
// *[Symbol.iterator]() {
// let node = this.head;
// while (node) {
// yield node;
// node = node.next;
// }
// }
}
@@ -0,0 +1,410 @@
import isValidNumber from '../isValid.js'
import parseDigits from '../helpers/parseDigits.js'
import matchPhoneNumberStringAgainstPhoneNumber from './matchPhoneNumberStringAgainstPhoneNumber.js'
import Metadata from '../metadata.js'
import getCountryByCallingCode from '../helpers/getCountryByCallingCode.js'
import { chooseFormatForNumber } from '../format.js'
import {
startsWith,
endsWith
} from './util.js'
/**
* Leniency when finding potential phone numbers in text segments
* The levels here are ordered in increasing strictness.
*/
export default
{
/**
* Phone numbers accepted are "possible", but not necessarily "valid".
*/
POSSIBLE(phoneNumber, { candidate, metadata })
{
return true
},
/**
* Phone numbers accepted are "possible" and "valid".
* Numbers written in national format must have their national-prefix
* present if it is usually written for a number of this type.
*/
VALID(phoneNumber, { candidate, defaultCountry, metadata })
{
if (
!phoneNumber.isValid() ||
!containsOnlyValidXChars(phoneNumber, candidate, metadata)
)
{
return false
}
// Skipped for simplicity.
// return isNationalPrefixPresentIfRequired(phoneNumber, { defaultCountry, metadata })
return true
},
/**
* Phone numbers accepted are "valid" and
* are grouped in a possible way for this locale. For example, a US number written as
* "65 02 53 00 00" and "650253 0000" are not accepted at this leniency level, whereas
* "650 253 0000", "650 2530000" or "6502530000" are.
* Numbers with more than one '/' symbol in the national significant number
* are also dropped at this level.
*
* Warning: This level might result in lower coverage especially for regions outside of
* country code "+1". If you are not sure about which level to use,
* email the discussion group libphonenumber-discuss@googlegroups.com.
*/
STRICT_GROUPING(phoneNumber, { candidate, defaultCountry, metadata, regExpCache })
{
if (
!phoneNumber.isValid() ||
!containsOnlyValidXChars(phoneNumber, candidate, metadata) ||
containsMoreThanOneSlashInNationalNumber(phoneNumber, candidate) ||
!isNationalPrefixPresentIfRequired(phoneNumber, { defaultCountry, metadata })
)
{
return false
}
return checkNumberGroupingIsValid
(
phoneNumber,
candidate,
metadata,
allNumberGroupsRemainGrouped,
regExpCache
)
},
/**
* Phone numbers accepted are "valid" and are grouped in the same way
* that we would have formatted it, or as a single block.
* For example, a US number written as "650 2530000" is not accepted
* at this leniency level, whereas "650 253 0000" or "6502530000" are.
* Numbers with more than one '/' symbol are also dropped at this level.
*
* Warning: This level might result in lower coverage especially for regions outside of
* country code "+1". If you are not sure about which level to use, email the discussion group
* libphonenumber-discuss@googlegroups.com.
*/
EXACT_GROUPING(phoneNumber, { candidate, defaultCountry, metadata, regExpCache })
{
if (
!phoneNumber.isValid() ||
!containsOnlyValidXChars(phoneNumber, candidate, metadata) ||
containsMoreThanOneSlashInNationalNumber(phoneNumber, candidate) ||
!isNationalPrefixPresentIfRequired(phoneNumber, { defaultCountry, metadata })
)
{
return false
}
return checkNumberGroupingIsValid
(
phoneNumber,
candidate,
metadata,
allNumberGroupsAreExactlyPresent,
regExpCache
)
}
}
function containsOnlyValidXChars(phoneNumber, candidate, metadata)
{
// The characters 'x' and 'X' can be (1) a carrier code, in which case they always precede the
// national significant number or (2) an extension sign, in which case they always precede the
// extension number. We assume a carrier code is more than 1 digit, so the first case has to
// have more than 1 consecutive 'x' or 'X', whereas the second case can only have exactly 1 'x'
// or 'X'. We ignore the character if it appears as the last character of the string.
for (let index = 0; index < candidate.length - 1; index++)
{
const charAtIndex = candidate.charAt(index)
if (charAtIndex === 'x' || charAtIndex === 'X')
{
const charAtNextIndex = candidate.charAt(index + 1)
if (charAtNextIndex === 'x' || charAtNextIndex === 'X')
{
// This is the carrier code case, in which the 'X's always precede the national
// significant number.
index++
if (matchPhoneNumberStringAgainstPhoneNumber(candidate.substring(index), phoneNumber, metadata) !== 'NSN_MATCH')
{
return false
}
// This is the extension sign case, in which the 'x' or 'X' should always precede the
// extension number.
}
else {
const ext = parseDigits(candidate.substring(index))
if (ext) {
if (phoneNumber.ext !== ext) {
return false
}
} else {
if (phoneNumber.ext) {
return false
}
}
}
}
}
return true
}
function isNationalPrefixPresentIfRequired(phoneNumber, { defaultCountry, metadata: _metadata })
{
// First, check how we deduced the country code. If it was written in international format, then
// the national prefix is not required.
if (phoneNumber.__countryCallingCodeSource !== 'FROM_DEFAULT_COUNTRY')
{
return true
}
const metadata = new Metadata(_metadata)
metadata.selectNumberingPlan(phoneNumber.countryCallingCode)
const phoneNumberRegion = phoneNumber.country || getCountryByCallingCode(phoneNumber.countryCallingCode, {
nationalNumber: phoneNumber.nationalNumber,
defaultCountry,
metadata
})
// Check if a national prefix should be present when formatting this number.
const nationalNumber = phoneNumber.nationalNumber
const format = chooseFormatForNumber(metadata.numberingPlan.formats(), nationalNumber)
// To do this, we check that a national prefix formatting rule was present
// and that it wasn't just the first-group symbol ($1) with punctuation.
if (format.nationalPrefixFormattingRule())
{
if (metadata.numberingPlan.nationalPrefixIsOptionalWhenFormattingInNationalFormat())
{
// The national-prefix is optional in these cases, so we don't need to check if it was present.
return true
}
if (!format.usesNationalPrefix())
{
// National Prefix not needed for this number.
return true
}
return Boolean(phoneNumber.nationalPrefix)
}
return true
}
export function containsMoreThanOneSlashInNationalNumber(phoneNumber, candidate)
{
const firstSlashInBodyIndex = candidate.indexOf('/')
if (firstSlashInBodyIndex < 0)
{
// No slashes, this is okay.
return false
}
// Now look for a second one.
const secondSlashInBodyIndex = candidate.indexOf('/', firstSlashInBodyIndex + 1)
if (secondSlashInBodyIndex < 0)
{
// Only one slash, this is okay.
return false
}
// If the first slash is after the country calling code, this is permitted.
const candidateHasCountryCode =
phoneNumber.__countryCallingCodeSource === 'FROM_NUMBER_WITH_PLUS_SIGN' ||
phoneNumber.__countryCallingCodeSource === 'FROM_NUMBER_WITHOUT_PLUS_SIGN'
if (candidateHasCountryCode && parseDigits(candidate.substring(0, firstSlashInBodyIndex)) === phoneNumber.countryCallingCode)
{
// Any more slashes and this is illegal.
return candidate.slice(secondSlashInBodyIndex + 1).indexOf('/') >= 0
}
return true
}
function checkNumberGroupingIsValid(
number,
candidate,
metadata,
checkGroups,
regExpCache
) {
throw new Error('This part of code hasn\'t been ported')
const normalizedCandidate = normalizeDigits(candidate, true /* keep non-digits */)
let formattedNumberGroups = getNationalNumberGroups(metadata, number, null)
if (checkGroups(metadata, number, normalizedCandidate, formattedNumberGroups)) {
return true
}
// If this didn't pass, see if there are any alternate formats that match, and try them instead.
const alternateFormats = MetadataManager.getAlternateFormatsForCountry(number.getCountryCode())
const nationalSignificantNumber = util.getNationalSignificantNumber(number)
if (alternateFormats) {
for (const alternateFormat of alternateFormats.numberFormats()) {
if (alternateFormat.leadingDigitsPatterns().length > 0) {
// There is only one leading digits pattern for alternate formats.
const leadingDigitsRegExp = regExpCache.getPatternForRegExp('^' + alternateFormat.leadingDigitsPatterns()[0])
if (!leadingDigitsRegExp.test(nationalSignificantNumber)) {
// Leading digits don't match; try another one.
continue
}
}
formattedNumberGroups = getNationalNumberGroups(metadata, number, alternateFormat)
if (checkGroups(metadata, number, normalizedCandidate, formattedNumberGroups)) {
return true
}
}
}
return false
}
/**
* Helper method to get the national-number part of a number, formatted without any national
* prefix, and return it as a set of digit blocks that would be formatted together following
* standard formatting rules.
*/
function getNationalNumberGroups(
metadata,
number,
formattingPattern
) {
throw new Error('This part of code hasn\'t been ported')
if (formattingPattern) {
// We format the NSN only, and split that according to the separator.
const nationalSignificantNumber = util.getNationalSignificantNumber(number)
return util.formatNsnUsingPattern(nationalSignificantNumber,
formattingPattern, 'RFC3966', metadata).split('-')
}
// This will be in the format +CC-DG1-DG2-DGX;ext=EXT where DG1..DGX represents groups of digits.
const rfc3966Format = formatNumber(number, 'RFC3966', metadata)
// We remove the extension part from the formatted string before splitting it into different
// groups.
let endIndex = rfc3966Format.indexOf(';')
if (endIndex < 0) {
endIndex = rfc3966Format.length
}
// The country-code will have a '-' following it.
const startIndex = rfc3966Format.indexOf('-') + 1
return rfc3966Format.slice(startIndex, endIndex).split('-')
}
function allNumberGroupsAreExactlyPresent
(
metadata,
number,
normalizedCandidate,
formattedNumberGroups
)
{
throw new Error('This part of code hasn\'t been ported')
const candidateGroups = normalizedCandidate.split(NON_DIGITS_PATTERN)
// Set this to the last group, skipping it if the number has an extension.
let candidateNumberGroupIndex =
number.hasExtension() ? candidateGroups.length - 2 : candidateGroups.length - 1
// First we check if the national significant number is formatted as a block.
// We use contains and not equals, since the national significant number may be present with
// a prefix such as a national number prefix, or the country code itself.
if (candidateGroups.length == 1
|| candidateGroups[candidateNumberGroupIndex].contains(
util.getNationalSignificantNumber(number)))
{
return true
}
// Starting from the end, go through in reverse, excluding the first group, and check the
// candidate and number groups are the same.
let formattedNumberGroupIndex = (formattedNumberGroups.length - 1)
while (formattedNumberGroupIndex > 0 && candidateNumberGroupIndex >= 0)
{
if (candidateGroups[candidateNumberGroupIndex] !== formattedNumberGroups[formattedNumberGroupIndex])
{
return false
}
formattedNumberGroupIndex--
candidateNumberGroupIndex--
}
// Now check the first group. There may be a national prefix at the start, so we only check
// that the candidate group ends with the formatted number group.
return (candidateNumberGroupIndex >= 0
&& endsWith(candidateGroups[candidateNumberGroupIndex], formattedNumberGroups[0]))
}
function allNumberGroupsRemainGrouped
(
metadata,
number,
normalizedCandidate,
formattedNumberGroups
)
{
throw new Error('This part of code hasn\'t been ported')
let fromIndex = 0
if (number.getCountryCodeSource() !== CountryCodeSource.FROM_DEFAULT_COUNTRY)
{
// First skip the country code if the normalized candidate contained it.
const countryCode = String(number.getCountryCode())
fromIndex = normalizedCandidate.indexOf(countryCode) + countryCode.length()
}
// Check each group of consecutive digits are not broken into separate groupings in the
// {@code normalizedCandidate} string.
for (let i = 0; i < formattedNumberGroups.length; i++)
{
// Fails if the substring of {@code normalizedCandidate} starting from {@code fromIndex}
// doesn't contain the consecutive digits in formattedNumberGroups[i].
fromIndex = normalizedCandidate.indexOf(formattedNumberGroups[i], fromIndex)
if (fromIndex < 0) {
return false
}
// Moves {@code fromIndex} forward.
fromIndex += formattedNumberGroups[i].length()
if (i == 0 && fromIndex < normalizedCandidate.length())
{
// We are at the position right after the NDC. We get the region used for formatting
// information based on the country code in the phone number, rather than the number itself,
// as we do not need to distinguish between different countries with the same country
// calling code and this is faster.
const region = util.getRegionCodeForCountryCode(number.getCountryCode())
if (util.getNddPrefixForRegion(region, true) != null
&& Character.isDigit(normalizedCandidate.charAt(fromIndex))) {
// This means there is no formatting symbol after the NDC. In this case, we only
// accept the number if there is no formatting symbol at all in the number, except
// for extensions. This is only important for countries with national prefixes.
const nationalSignificantNumber = util.getNationalSignificantNumber(number)
return startsWith
(
normalizedCandidate.slice(fromIndex - formattedNumberGroups[i].length),
nationalSignificantNumber
)
}
}
}
// The check here makes sure that we haven't mistakenly already used the extension to
// match the last group of the subscriber number. Note the extension cannot have
// formatting in-between digits.
return normalizedCandidate.slice(fromIndex).contains(number.getExtension())
}
@@ -0,0 +1,35 @@
/*
import { containsMoreThanOneSlashInNationalNumber } from './Leniency.js'
describe('Leniency', () => {
it('testContainsMoreThanOneSlashInNationalNumber', () => {
// A date should return true.
number.setCountryCode(1)
number.setCountryCodeSource(CountryCodeSource.FROM_DEFAULT_COUNTRY)
containsMoreThanOneSlashInNationalNumber(number, '1/05/2013').should.equal(true)
// Here, the country code source thinks it started with a country calling code, but this is not
// the same as the part before the slash, so it's still true.
number.setCountryCode(274)
number.setCountryCodeSource(CountryCodeSource.FROM_NUMBER_WITHOUT_PLUS_SIGN)
containsMoreThanOneSlashInNationalNumber(number, '27/4/2013').should.equal(true)
// Now it should be false, because the first slash is after the country calling code.
number.setCountryCode(49)
number.setCountryCodeSource(CountryCodeSource.FROM_NUMBER_WITH_PLUS_SIGN)
containsMoreThanOneSlashInNationalNumber(number, '49/69/2013').should.equal(false)
number.setCountryCode(49)
number.setCountryCodeSource(CountryCodeSource.FROM_NUMBER_WITHOUT_PLUS_SIGN)
containsMoreThanOneSlashInNationalNumber(number, '+49/69/2013').should.equal(false)
containsMoreThanOneSlashInNationalNumber(number, '+ 49/69/2013').should.equal(false)
containsMoreThanOneSlashInNationalNumber(number, '+ 49/69/20/13').should.equal(true)
// Here, the first group is not assumed to be the country calling code, even though it is the
// same as it, so this should return true.
number.setCountryCode(49)
number.setCountryCodeSource(CountryCodeSource.FROM_DEFAULT_COUNTRY)
containsMoreThanOneSlashInNationalNumber(number, '49/69/2013').should.equal(true)
})
})
*/
@@ -0,0 +1,20 @@
import LRUCache from './LRUCache.js'
// A cache for frequently used country-specific regular expressions. Set to 32 to cover ~2-3
// countries being used for the same doc with ~10 patterns for each country. Some pages will have
// a lot more countries in use, but typically fewer numbers for each so expanding the cache for
// that use-case won't have a lot of benefit.
export default class RegExpCache {
constructor(size) {
this.cache = new LRUCache(size)
}
getPatternForRegExp(pattern) {
let regExp = this.cache.get(pattern)
if (!regExp) {
regExp = new RegExp('^' + pattern)
this.cache.put(pattern, regExp)
}
return regExp
}
}
@@ -0,0 +1,86 @@
// Copy-pasted from `PhoneNumberMatcher.js`.
import { PLUS_CHARS } from '../constants.js'
import { limit } from './util.js'
import {
isLatinLetter,
isInvalidPunctuationSymbol
} from './utf-8.js'
const OPENING_PARENS = '(\\[\uFF08\uFF3B'
const CLOSING_PARENS = ')\\]\uFF09\uFF3D'
const NON_PARENS = `[^${OPENING_PARENS}${CLOSING_PARENS}]`
export const LEAD_CLASS = `[${OPENING_PARENS}${PLUS_CHARS}]`
// Punctuation that may be at the start of a phone number - brackets and plus signs.
const LEAD_CLASS_LEADING = new RegExp('^' + LEAD_CLASS)
// Limit on the number of pairs of brackets in a phone number.
const BRACKET_PAIR_LIMIT = limit(0, 3)
/**
* Pattern to check that brackets match. Opening brackets should be closed within a phone number.
* This also checks that there is something inside the brackets. Having no brackets at all is also
* fine.
*
* An opening bracket at the beginning may not be closed, but subsequent ones should be. It's
* also possible that the leading bracket was dropped, so we shouldn't be surprised if we see a
* closing bracket first. We limit the sets of brackets in a phone number to four.
*/
const MATCHING_BRACKETS_ENTIRE = new RegExp
(
'^'
+ "(?:[" + OPENING_PARENS + "])?" + "(?:" + NON_PARENS + "+" + "[" + CLOSING_PARENS + "])?"
+ NON_PARENS + "+"
+ "(?:[" + OPENING_PARENS + "]" + NON_PARENS + "+[" + CLOSING_PARENS + "])" + BRACKET_PAIR_LIMIT
+ NON_PARENS + "*"
+ '$'
)
/**
* Matches strings that look like publication pages. Example:
* <pre>Computing Complete Answers to Queries in the Presence of Limited Access Patterns.
* Chen Li. VLDB J. 12(3): 211-227 (2003).</pre>
*
* The string "211-227 (2003)" is not a telephone number.
*/
const PUB_PAGES = /\d{1,5}-+\d{1,5}\s{0,4}\(\d{1,4}/
export default function isValidCandidate(candidate, offset, text, leniency)
{
// Check the candidate doesn't contain any formatting
// which would indicate that it really isn't a phone number.
if (!MATCHING_BRACKETS_ENTIRE.test(candidate) || PUB_PAGES.test(candidate)) {
return
}
// If leniency is set to VALID or stricter, we also want to skip numbers that are surrounded
// by Latin alphabetic characters, to skip cases like abc8005001234 or 8005001234def.
if (leniency !== 'POSSIBLE')
{
// If the candidate is not at the start of the text,
// and does not start with phone-number punctuation,
// check the previous character.
if (offset > 0 && !LEAD_CLASS_LEADING.test(candidate))
{
const previousChar = text[offset - 1]
// We return null if it is a latin letter or an invalid punctuation symbol.
if (isInvalidPunctuationSymbol(previousChar) || isLatinLetter(previousChar)) {
return false
}
}
const lastCharIndex = offset + candidate.length
if (lastCharIndex < text.length)
{
const nextChar = text[lastCharIndex]
if (isInvalidPunctuationSymbol(nextChar) || isLatinLetter(nextChar)) {
return false
}
}
}
return true
}
@@ -0,0 +1,29 @@
// Matches strings that look like dates using "/" as a separator.
// Examples: 3/10/2011, 31/10/96 or 08/31/95.
const SLASH_SEPARATED_DATES = /(?:(?:[0-3]?\d\/[01]?\d)|(?:[01]?\d\/[0-3]?\d))\/(?:[12]\d)?\d{2}/
// Matches timestamps.
// Examples: "2012-01-02 08:00".
// Note that the reg-ex does not include the
// trailing ":\d\d" -- that is covered by TIME_STAMPS_SUFFIX.
const TIME_STAMPS = /[12]\d{3}[-/]?[01]\d[-/]?[0-3]\d +[0-2]\d$/
const TIME_STAMPS_SUFFIX_LEADING = /^:[0-5]\d/
export default function isValidPreCandidate(candidate, offset, text)
{
// Skip a match that is more likely to be a date.
if (SLASH_SEPARATED_DATES.test(candidate)) {
return false
}
// Skip potential time-stamps.
if (TIME_STAMPS.test(candidate))
{
const followingText = text.slice(offset + candidate.length)
if (TIME_STAMPS_SUFFIX_LEADING.test(followingText)) {
return false
}
}
return true
}
@@ -0,0 +1,64 @@
import parsePhoneNumber from '../parsePhoneNumber.js'
/**
* Matches a phone number object against a phone number string.
* @param {string} phoneNumberString
* @param {PhoneNumber} phoneNumber
* @param {object} metadata — Metadata JSON
* @return {'INVALID_NUMBER'|'NO_MATCH'|'SHORT_NSN_MATCH'|'NSN_MATCH'|'EXACT_MATCH'}
*/
export default function matchPhoneNumberStringAgainstPhoneNumber(phoneNumberString, phoneNumber, metadata) {
// Parse `phoneNumberString`.
let phoneNumberStringContainsCallingCode = true
let parsedPhoneNumber = parsePhoneNumber(phoneNumberString, metadata)
if (!parsedPhoneNumber) {
// If `phoneNumberString` didn't contain a country calling code
// then substitute it with the `phoneNumber`'s country calling code.
phoneNumberStringContainsCallingCode = false
parsedPhoneNumber = parsePhoneNumber(phoneNumberString, { defaultCallingCode: phoneNumber.countryCallingCode }, metadata)
}
if (!parsedPhoneNumber) {
return 'INVALID_NUMBER'
}
// Check that the extensions match.
if (phoneNumber.ext) {
if (parsedPhoneNumber.ext !== phoneNumber.ext) {
return 'NO_MATCH'
}
} else {
if (parsedPhoneNumber.ext) {
return 'NO_MATCH'
}
}
// Check that country calling codes match.
if (phoneNumberStringContainsCallingCode) {
if (phoneNumber.countryCallingCode !== parsedPhoneNumber.countryCallingCode) {
return 'NO_MATCH'
}
}
// Check if the whole numbers match.
if (phoneNumber.number === parsedPhoneNumber.number) {
if (phoneNumberStringContainsCallingCode) {
return 'EXACT_MATCH'
} else {
return 'NSN_MATCH'
}
}
// Check if one national number is a "suffix" of the other.
if (
phoneNumber.nationalNumber.indexOf(parsedPhoneNumber.nationalNumber) === 0 ||
parsedPhoneNumber.nationalNumber.indexOf(phoneNumber.nationalNumber) === 0
) {
// "A SHORT_NSN_MATCH occurs if there is a difference because of the
// presence or absence of an 'Italian leading zero', the presence or
// absence of an extension, or one NSN being a shorter variant of the
// other."
return 'SHORT_NSN_MATCH'
}
return 'NO_MATCH'
}
@@ -0,0 +1,19 @@
import { trimAfterFirstMatch } from './util.js'
// Regular expression of characters typically used to start a second phone number for the purposes
// of parsing. This allows us to strip off parts of the number that are actually the start of
// another number, such as for: (530) 583-6985 x302/x2303 -> the second extension here makes this
// actually two phone numbers, (530) 583-6985 x302 and (530) 583-6985 x2303. We remove the second
// extension so that the first number is parsed correctly.
//
// Matches a slash (\ or /) followed by a space followed by an `x`.
//
const SECOND_NUMBER_START_PATTERN = /[\\/] *x/
export default function parsePreCandidate(candidate)
{
// Check for extra numbers at the end.
// TODO: This is the place to start when trying to support extraction of multiple phone number
// from split notations (+41 79 123 45 67 / 68).
return trimAfterFirstMatch(SECOND_NUMBER_START_PATTERN, candidate)
}
@@ -0,0 +1,82 @@
// Javascript doesn't support UTF-8 regular expressions.
// So mimicking them here.
// Copy-pasted from `PhoneNumberMatcher.js`.
/**
* "\p{Z}" is any kind of whitespace or invisible separator ("Separator").
* http://www.regular-expressions.info/unicode.html
* "\P{Z}" is the reverse of "\p{Z}".
* "\p{N}" is any kind of numeric character in any script ("Number").
* "\p{Nd}" is a digit zero through nine in any script except "ideographic scripts" ("Decimal_Digit_Number").
* "\p{Sc}" is a currency symbol ("Currency_Symbol").
* "\p{L}" is any kind of letter from any language ("Letter").
* "\p{Mn}" is "non-spacing mark".
*
* Javascript doesn't support Unicode Regular Expressions
* so substituting it with this explicit set of characters.
*
* https://stackoverflow.com/questions/13210194/javascript-regex-equivalent-of-a-za-z-using-pl
* https://github.com/danielberndt/babel-plugin-utf-8-regex/blob/master/src/transformer.js
*/
const _pZ = '\u0020\u00A0\u1680\u180E\u2000-\u200A\u2028\u2029\u202F\u205F\u3000'
export const pZ = `[${_pZ}]`
export const PZ = `[^${_pZ}]`
export const _pN = '\u0030-\u0039\u00B2\u00B3\u00B9\u00BC-\u00BE\u0660-\u0669\u06F0-\u06F9\u07C0-\u07C9\u0966-\u096F\u09E6-\u09EF\u09F4-\u09F9\u0A66-\u0A6F\u0AE6-\u0AEF\u0B66-\u0B6F\u0B72-\u0B77\u0BE6-\u0BF2\u0C66-\u0C6F\u0C78-\u0C7E\u0CE6-\u0CEF\u0D66-\u0D75\u0E50-\u0E59\u0ED0-\u0ED9\u0F20-\u0F33\u1040-\u1049\u1090-\u1099\u1369-\u137C\u16EE-\u16F0\u17E0-\u17E9\u17F0-\u17F9\u1810-\u1819\u1946-\u194F\u19D0-\u19DA\u1A80-\u1A89\u1A90-\u1A99\u1B50-\u1B59\u1BB0-\u1BB9\u1C40-\u1C49\u1C50-\u1C59\u2070\u2074-\u2079\u2080-\u2089\u2150-\u2182\u2185-\u2189\u2460-\u249B\u24EA-\u24FF\u2776-\u2793\u2CFD\u3007\u3021-\u3029\u3038-\u303A\u3192-\u3195\u3220-\u3229\u3248-\u324F\u3251-\u325F\u3280-\u3289\u32B1-\u32BF\uA620-\uA629\uA6E6-\uA6EF\uA830-\uA835\uA8D0-\uA8D9\uA900-\uA909\uA9D0-\uA9D9\uAA50-\uAA59\uABF0-\uABF9\uFF10-\uFF19'
// const pN = `[${_pN}]`
const _pNd = '\u0030-\u0039\u0660-\u0669\u06F0-\u06F9\u07C0-\u07C9\u0966-\u096F\u09E6-\u09EF\u0A66-\u0A6F\u0AE6-\u0AEF\u0B66-\u0B6F\u0BE6-\u0BEF\u0C66-\u0C6F\u0CE6-\u0CEF\u0D66-\u0D6F\u0E50-\u0E59\u0ED0-\u0ED9\u0F20-\u0F29\u1040-\u1049\u1090-\u1099\u17E0-\u17E9\u1810-\u1819\u1946-\u194F\u19D0-\u19D9\u1A80-\u1A89\u1A90-\u1A99\u1B50-\u1B59\u1BB0-\u1BB9\u1C40-\u1C49\u1C50-\u1C59\uA620-\uA629\uA8D0-\uA8D9\uA900-\uA909\uA9D0-\uA9D9\uAA50-\uAA59\uABF0-\uABF9\uFF10-\uFF19'
export const pNd = `[${_pNd}]`
export const _pL = '\u0041-\u005A\u0061-\u007A\u00AA\u00B5\u00BA\u00C0-\u00D6\u00D8-\u00F6\u00F8-\u02C1\u02C6-\u02D1\u02E0-\u02E4\u02EC\u02EE\u0370-\u0374\u0376\u0377\u037A-\u037D\u0386\u0388-\u038A\u038C\u038E-\u03A1\u03A3-\u03F5\u03F7-\u0481\u048A-\u0527\u0531-\u0556\u0559\u0561-\u0587\u05D0-\u05EA\u05F0-\u05F2\u0620-\u064A\u066E\u066F\u0671-\u06D3\u06D5\u06E5\u06E6\u06EE\u06EF\u06FA-\u06FC\u06FF\u0710\u0712-\u072F\u074D-\u07A5\u07B1\u07CA-\u07EA\u07F4\u07F5\u07FA\u0800-\u0815\u081A\u0824\u0828\u0840-\u0858\u08A0\u08A2-\u08AC\u0904-\u0939\u093D\u0950\u0958-\u0961\u0971-\u0977\u0979-\u097F\u0985-\u098C\u098F\u0990\u0993-\u09A8\u09AA-\u09B0\u09B2\u09B6-\u09B9\u09BD\u09CE\u09DC\u09DD\u09DF-\u09E1\u09F0\u09F1\u0A05-\u0A0A\u0A0F\u0A10\u0A13-\u0A28\u0A2A-\u0A30\u0A32\u0A33\u0A35\u0A36\u0A38\u0A39\u0A59-\u0A5C\u0A5E\u0A72-\u0A74\u0A85-\u0A8D\u0A8F-\u0A91\u0A93-\u0AA8\u0AAA-\u0AB0\u0AB2\u0AB3\u0AB5-\u0AB9\u0ABD\u0AD0\u0AE0\u0AE1\u0B05-\u0B0C\u0B0F\u0B10\u0B13-\u0B28\u0B2A-\u0B30\u0B32\u0B33\u0B35-\u0B39\u0B3D\u0B5C\u0B5D\u0B5F-\u0B61\u0B71\u0B83\u0B85-\u0B8A\u0B8E-\u0B90\u0B92-\u0B95\u0B99\u0B9A\u0B9C\u0B9E\u0B9F\u0BA3\u0BA4\u0BA8-\u0BAA\u0BAE-\u0BB9\u0BD0\u0C05-\u0C0C\u0C0E-\u0C10\u0C12-\u0C28\u0C2A-\u0C33\u0C35-\u0C39\u0C3D\u0C58\u0C59\u0C60\u0C61\u0C85-\u0C8C\u0C8E-\u0C90\u0C92-\u0CA8\u0CAA-\u0CB3\u0CB5-\u0CB9\u0CBD\u0CDE\u0CE0\u0CE1\u0CF1\u0CF2\u0D05-\u0D0C\u0D0E-\u0D10\u0D12-\u0D3A\u0D3D\u0D4E\u0D60\u0D61\u0D7A-\u0D7F\u0D85-\u0D96\u0D9A-\u0DB1\u0DB3-\u0DBB\u0DBD\u0DC0-\u0DC6\u0E01-\u0E30\u0E32\u0E33\u0E40-\u0E46\u0E81\u0E82\u0E84\u0E87\u0E88\u0E8A\u0E8D\u0E94-\u0E97\u0E99-\u0E9F\u0EA1-\u0EA3\u0EA5\u0EA7\u0EAA\u0EAB\u0EAD-\u0EB0\u0EB2\u0EB3\u0EBD\u0EC0-\u0EC4\u0EC6\u0EDC-\u0EDF\u0F00\u0F40-\u0F47\u0F49-\u0F6C\u0F88-\u0F8C\u1000-\u102A\u103F\u1050-\u1055\u105A-\u105D\u1061\u1065\u1066\u106E-\u1070\u1075-\u1081\u108E\u10A0-\u10C5\u10C7\u10CD\u10D0-\u10FA\u10FC-\u1248\u124A-\u124D\u1250-\u1256\u1258\u125A-\u125D\u1260-\u1288\u128A-\u128D\u1290-\u12B0\u12B2-\u12B5\u12B8-\u12BE\u12C0\u12C2-\u12C5\u12C8-\u12D6\u12D8-\u1310\u1312-\u1315\u1318-\u135A\u1380-\u138F\u13A0-\u13F4\u1401-\u166C\u166F-\u167F\u1681-\u169A\u16A0-\u16EA\u1700-\u170C\u170E-\u1711\u1720-\u1731\u1740-\u1751\u1760-\u176C\u176E-\u1770\u1780-\u17B3\u17D7\u17DC\u1820-\u1877\u1880-\u18A8\u18AA\u18B0-\u18F5\u1900-\u191C\u1950-\u196D\u1970-\u1974\u1980-\u19AB\u19C1-\u19C7\u1A00-\u1A16\u1A20-\u1A54\u1AA7\u1B05-\u1B33\u1B45-\u1B4B\u1B83-\u1BA0\u1BAE\u1BAF\u1BBA-\u1BE5\u1C00-\u1C23\u1C4D-\u1C4F\u1C5A-\u1C7D\u1CE9-\u1CEC\u1CEE-\u1CF1\u1CF5\u1CF6\u1D00-\u1DBF\u1E00-\u1F15\u1F18-\u1F1D\u1F20-\u1F45\u1F48-\u1F4D\u1F50-\u1F57\u1F59\u1F5B\u1F5D\u1F5F-\u1F7D\u1F80-\u1FB4\u1FB6-\u1FBC\u1FBE\u1FC2-\u1FC4\u1FC6-\u1FCC\u1FD0-\u1FD3\u1FD6-\u1FDB\u1FE0-\u1FEC\u1FF2-\u1FF4\u1FF6-\u1FFC\u2071\u207F\u2090-\u209C\u2102\u2107\u210A-\u2113\u2115\u2119-\u211D\u2124\u2126\u2128\u212A-\u212D\u212F-\u2139\u213C-\u213F\u2145-\u2149\u214E\u2183\u2184\u2C00-\u2C2E\u2C30-\u2C5E\u2C60-\u2CE4\u2CEB-\u2CEE\u2CF2\u2CF3\u2D00-\u2D25\u2D27\u2D2D\u2D30-\u2D67\u2D6F\u2D80-\u2D96\u2DA0-\u2DA6\u2DA8-\u2DAE\u2DB0-\u2DB6\u2DB8-\u2DBE\u2DC0-\u2DC6\u2DC8-\u2DCE\u2DD0-\u2DD6\u2DD8-\u2DDE\u2E2F\u3005\u3006\u3031-\u3035\u303B\u303C\u3041-\u3096\u309D-\u309F\u30A1-\u30FA\u30FC-\u30FF\u3105-\u312D\u3131-\u318E\u31A0-\u31BA\u31F0-\u31FF\u3400-\u4DB5\u4E00-\u9FCC\uA000-\uA48C\uA4D0-\uA4FD\uA500-\uA60C\uA610-\uA61F\uA62A\uA62B\uA640-\uA66E\uA67F-\uA697\uA6A0-\uA6E5\uA717-\uA71F\uA722-\uA788\uA78B-\uA78E\uA790-\uA793\uA7A0-\uA7AA\uA7F8-\uA801\uA803-\uA805\uA807-\uA80A\uA80C-\uA822\uA840-\uA873\uA882-\uA8B3\uA8F2-\uA8F7\uA8FB\uA90A-\uA925\uA930-\uA946\uA960-\uA97C\uA984-\uA9B2\uA9CF\uAA00-\uAA28\uAA40-\uAA42\uAA44-\uAA4B\uAA60-\uAA76\uAA7A\uAA80-\uAAAF\uAAB1\uAAB5\uAAB6\uAAB9-\uAABD\uAAC0\uAAC2\uAADB-\uAADD\uAAE0-\uAAEA\uAAF2-\uAAF4\uAB01-\uAB06\uAB09-\uAB0E\uAB11-\uAB16\uAB20-\uAB26\uAB28-\uAB2E\uABC0-\uABE2\uAC00-\uD7A3\uD7B0-\uD7C6\uD7CB-\uD7FB\uF900-\uFA6D\uFA70-\uFAD9\uFB00-\uFB06\uFB13-\uFB17\uFB1D\uFB1F-\uFB28\uFB2A-\uFB36\uFB38-\uFB3C\uFB3E\uFB40\uFB41\uFB43\uFB44\uFB46-\uFBB1\uFBD3-\uFD3D\uFD50-\uFD8F\uFD92-\uFDC7\uFDF0-\uFDFB\uFE70-\uFE74\uFE76-\uFEFC\uFF21-\uFF3A\uFF41-\uFF5A\uFF66-\uFFBE\uFFC2-\uFFC7\uFFCA-\uFFCF\uFFD2-\uFFD7\uFFDA-\uFFDC'
const pL = `[${_pL}]`
const pL_regexp = new RegExp(pL)
const _pSc = '\u0024\u00A2-\u00A5\u058F\u060B\u09F2\u09F3\u09FB\u0AF1\u0BF9\u0E3F\u17DB\u20A0-\u20B9\uA838\uFDFC\uFE69\uFF04\uFFE0\uFFE1\uFFE5\uFFE6'
const pSc = `[${_pSc}]`
const pSc_regexp = new RegExp(pSc)
const _pMn = '\u0300-\u036F\u0483-\u0487\u0591-\u05BD\u05BF\u05C1\u05C2\u05C4\u05C5\u05C7\u0610-\u061A\u064B-\u065F\u0670\u06D6-\u06DC\u06DF-\u06E4\u06E7\u06E8\u06EA-\u06ED\u0711\u0730-\u074A\u07A6-\u07B0\u07EB-\u07F3\u0816-\u0819\u081B-\u0823\u0825-\u0827\u0829-\u082D\u0859-\u085B\u08E4-\u08FE\u0900-\u0902\u093A\u093C\u0941-\u0948\u094D\u0951-\u0957\u0962\u0963\u0981\u09BC\u09C1-\u09C4\u09CD\u09E2\u09E3\u0A01\u0A02\u0A3C\u0A41\u0A42\u0A47\u0A48\u0A4B-\u0A4D\u0A51\u0A70\u0A71\u0A75\u0A81\u0A82\u0ABC\u0AC1-\u0AC5\u0AC7\u0AC8\u0ACD\u0AE2\u0AE3\u0B01\u0B3C\u0B3F\u0B41-\u0B44\u0B4D\u0B56\u0B62\u0B63\u0B82\u0BC0\u0BCD\u0C3E-\u0C40\u0C46-\u0C48\u0C4A-\u0C4D\u0C55\u0C56\u0C62\u0C63\u0CBC\u0CBF\u0CC6\u0CCC\u0CCD\u0CE2\u0CE3\u0D41-\u0D44\u0D4D\u0D62\u0D63\u0DCA\u0DD2-\u0DD4\u0DD6\u0E31\u0E34-\u0E3A\u0E47-\u0E4E\u0EB1\u0EB4-\u0EB9\u0EBB\u0EBC\u0EC8-\u0ECD\u0F18\u0F19\u0F35\u0F37\u0F39\u0F71-\u0F7E\u0F80-\u0F84\u0F86\u0F87\u0F8D-\u0F97\u0F99-\u0FBC\u0FC6\u102D-\u1030\u1032-\u1037\u1039\u103A\u103D\u103E\u1058\u1059\u105E-\u1060\u1071-\u1074\u1082\u1085\u1086\u108D\u109D\u135D-\u135F\u1712-\u1714\u1732-\u1734\u1752\u1753\u1772\u1773\u17B4\u17B5\u17B7-\u17BD\u17C6\u17C9-\u17D3\u17DD\u180B-\u180D\u18A9\u1920-\u1922\u1927\u1928\u1932\u1939-\u193B\u1A17\u1A18\u1A56\u1A58-\u1A5E\u1A60\u1A62\u1A65-\u1A6C\u1A73-\u1A7C\u1A7F\u1B00-\u1B03\u1B34\u1B36-\u1B3A\u1B3C\u1B42\u1B6B-\u1B73\u1B80\u1B81\u1BA2-\u1BA5\u1BA8\u1BA9\u1BAB\u1BE6\u1BE8\u1BE9\u1BED\u1BEF-\u1BF1\u1C2C-\u1C33\u1C36\u1C37\u1CD0-\u1CD2\u1CD4-\u1CE0\u1CE2-\u1CE8\u1CED\u1CF4\u1DC0-\u1DE6\u1DFC-\u1DFF\u20D0-\u20DC\u20E1\u20E5-\u20F0\u2CEF-\u2CF1\u2D7F\u2DE0-\u2DFF\u302A-\u302D\u3099\u309A\uA66F\uA674-\uA67D\uA69F\uA6F0\uA6F1\uA802\uA806\uA80B\uA825\uA826\uA8C4\uA8E0-\uA8F1\uA926-\uA92D\uA947-\uA951\uA980-\uA982\uA9B3\uA9B6-\uA9B9\uA9BC\uAA29-\uAA2E\uAA31\uAA32\uAA35\uAA36\uAA43\uAA4C\uAAB0\uAAB2-\uAAB4\uAAB7\uAAB8\uAABE\uAABF\uAAC1\uAAEC\uAAED\uAAF6\uABE5\uABE8\uABED\uFB1E\uFE00-\uFE0F\uFE20-\uFE26'
const pMn = `[${_pMn}]`
const pMn_regexp = new RegExp(pMn)
const _InBasic_Latin = '\u0000-\u007F'
const _InLatin_1_Supplement = '\u0080-\u00FF'
const _InLatin_Extended_A = '\u0100-\u017F'
const _InLatin_Extended_Additional = '\u1E00-\u1EFF'
const _InLatin_Extended_B = '\u0180-\u024F'
const _InCombining_Diacritical_Marks = '\u0300-\u036F'
const latinLetterRegexp = new RegExp
(
'[' +
_InBasic_Latin +
_InLatin_1_Supplement +
_InLatin_Extended_A +
_InLatin_Extended_Additional +
_InLatin_Extended_B +
_InCombining_Diacritical_Marks +
']'
)
/**
* Helper method to determine if a character is a Latin-script letter or not.
* For our purposes, combining marks should also return true since we assume
* they have been added to a preceding Latin character.
*/
export function isLatinLetter(letter)
{
// Combining marks are a subset of non-spacing-mark.
if (!pL_regexp.test(letter) && !pMn_regexp.test(letter)) {
return false
}
return latinLetterRegexp.test(letter)
}
export function isInvalidPunctuationSymbol(character)
{
return character === '%' || pSc_regexp.test(character)
}
@@ -0,0 +1,33 @@
/** Returns a regular expression quantifier with an upper and lower limit. */
export function limit(lower, upper)
{
if ((lower < 0) || (upper <= 0) || (upper < lower)) {
throw new TypeError()
}
return `{${lower},${upper}}`
}
/**
* Trims away any characters after the first match of {@code pattern} in {@code candidate},
* returning the trimmed version.
*/
export function trimAfterFirstMatch(regexp, string)
{
const index = string.search(regexp)
if (index >= 0) {
return string.slice(0, index)
}
return string
}
export function startsWith(string, substring)
{
return string.indexOf(substring) === 0
}
export function endsWith(string, substring)
{
return string.indexOf(substring, string.length - substring.length) === string.length - substring.length
}
@@ -0,0 +1,39 @@
import {
limit,
trimAfterFirstMatch,
startsWith,
endsWith
} from './util.js'
describe('findNumbers/util', () =>
{
it('should generate regexp limit', () =>
{
let thrower = () => limit(1, 0)
thrower.should.throw()
thrower = () => limit(-1, 1)
thrower.should.throw()
thrower = () => limit(0, 0)
thrower.should.throw()
})
it('should trimAfterFirstMatch', () =>
{
trimAfterFirstMatch(/\d/, 'abc123').should.equal('abc')
trimAfterFirstMatch(/\d/, 'abc').should.equal('abc')
})
it('should determine if a string starts with a substring', () =>
{
startsWith('𐍈123', '𐍈').should.equal(true)
startsWith('1𐍈', '𐍈').should.equal(false)
})
it('should determine if a string ends with a substring', () =>
{
endsWith('123𐍈', '𐍈').should.equal(true)
endsWith('𐍈1', '𐍈').should.equal(false)
})
})