Skip to main content

date-extractors

Documentation / extractor/html-to-cite/extract-date/date-extractors

DATE_EXPRESSIONS​

const DATE_EXPRESSIONS: string;

Defined in: packages/ai-research-agent/src/extractor/html-to-cite/extract-date/date-extractors.js:40

Alternative JavaScript-based selector approach (faster in some browsers)


FAST_PREPEND​

const FAST_PREPEND: "" = '';

Defined in: packages/ai-research-agent/src/extractor/html-to-cite/extract-date/date-extractors.js:30

Note: FAST_PREPEND would need to be defined separately


SLOW_PREPEND​

const SLOW_PREPEND: "" = "";

Defined in: packages/ai-research-agent/src/extractor/html-to-cite/extract-date/date-extractors.js:74

XPath-style expressions


FREE_TEXT_EXPRESSIONS​

const FREE_TEXT_EXPRESSIONS: ".//*[self::div or self::h2 or self::h3 or self::h4 or self::li or self::p or self::span or self::time or self::ul]/text()" = ".//*[self::div or self::h2 or self::h3 or self::h4 or self::li or self::p or self::span or self::time or self::ul]/text()";

Defined in: packages/ai-research-agent/src/extractor/html-to-cite/extract-date/date-extractors.js:80


MAX_SEGMENT_LEN​

const MAX_SEGMENT_LEN: 52 = 52;

Defined in: packages/ai-research-agent/src/extractor/html-to-cite/extract-date/date-extractors.js:34


MIN_SEGMENT_LEN​

const MIN_SEGMENT_LEN: 6 = 6;

Defined in: packages/ai-research-agent/src/extractor/html-to-cite/extract-date/date-extractors.js:33

Segment length constraints


YEAR_PATTERN​

const YEAR_PATTERN: RegExp;

Defined in: packages/ai-research-agent/src/extractor/html-to-cite/extract-date/date-extractors.js:88

Search patterns


YMD_PATTERN​

const YMD_PATTERN: RegExp;

Defined in: packages/ai-research-agent/src/extractor/html-to-cite/extract-date/date-extractors.js:109


const COPYRIGHT_PATTERN: RegExp;

Defined in: packages/ai-research-agent/src/extractor/html-to-cite/extract-date/date-extractors.js:89


TIMESTAMP_PATTERN​

const TIMESTAMP_PATTERN: RegExp;

Defined in: packages/ai-research-agent/src/extractor/html-to-cite/extract-date/date-extractors.js:140


THREE_PATTERN​

const THREE_PATTERN: RegExp;

Defined in: packages/ai-research-agent/src/extractor/html-to-cite/extract-date/date-extractors.js:90


THREE_CATCH​

const THREE_CATCH: RegExp;

Defined in: packages/ai-research-agent/src/extractor/html-to-cite/extract-date/date-extractors.js:91


THREE_LOOSE_PATTERN​

const THREE_LOOSE_PATTERN: RegExp;

Defined in: packages/ai-research-agent/src/extractor/html-to-cite/extract-date/date-extractors.js:92


THREE_LOOSE_CATCH​

const THREE_LOOSE_CATCH: RegExp;

Defined in: packages/ai-research-agent/src/extractor/html-to-cite/extract-date/date-extractors.js:93


SELECT_YMD_PATTERN​

const SELECT_YMD_PATTERN: RegExp;

Defined in: packages/ai-research-agent/src/extractor/html-to-cite/extract-date/date-extractors.js:94


SELECT_YMD_YEAR​

const SELECT_YMD_YEAR: RegExp;

Defined in: packages/ai-research-agent/src/extractor/html-to-cite/extract-date/date-extractors.js:95


YMD_YEAR​

const YMD_YEAR: RegExp;

Defined in: packages/ai-research-agent/src/extractor/html-to-cite/extract-date/date-extractors.js:96


DATESTRINGS_PATTERN​

const DATESTRINGS_PATTERN: RegExp;

Defined in: packages/ai-research-agent/src/extractor/html-to-cite/extract-date/date-extractors.js:97


DATESTRINGS_CATCH​

const DATESTRINGS_CATCH: RegExp;

Defined in: packages/ai-research-agent/src/extractor/html-to-cite/extract-date/date-extractors.js:98


SLASHES_PATTERN​

const SLASHES_PATTERN: RegExp;

Defined in: packages/ai-research-agent/src/extractor/html-to-cite/extract-date/date-extractors.js:99


SLASHES_YEAR​

const SLASHES_YEAR: RegExp;

Defined in: packages/ai-research-agent/src/extractor/html-to-cite/extract-date/date-extractors.js:100


YYYYMM_PATTERN​

const YYYYMM_PATTERN: RegExp;

Defined in: packages/ai-research-agent/src/extractor/html-to-cite/extract-date/date-extractors.js:101


YYYYMM_CATCH​

const YYYYMM_CATCH: RegExp;

Defined in: packages/ai-research-agent/src/extractor/html-to-cite/extract-date/date-extractors.js:102


MMYYYY_PATTERN​

const MMYYYY_PATTERN: RegExp;

Defined in: packages/ai-research-agent/src/extractor/html-to-cite/extract-date/date-extractors.js:103


MMYYYY_YEAR​

const MMYYYY_YEAR: RegExp;

Defined in: packages/ai-research-agent/src/extractor/html-to-cite/extract-date/date-extractors.js:104


SIMPLE_PATTERN​

const SIMPLE_PATTERN: RegExp;

Defined in: packages/ai-research-agent/src/extractor/html-to-cite/extract-date/date-extractors.js:105


THREE_COMP_REGEX_A​

const THREE_COMP_REGEX_A: RegExp;

Defined in: packages/ai-research-agent/src/extractor/html-to-cite/extract-date/date-extractors.js:83

Core regex patterns


THREE_COMP_REGEX_B​

const THREE_COMP_REGEX_B: RegExp;

Defined in: packages/ai-research-agent/src/extractor/html-to-cite/extract-date/date-extractors.js:84


TWO_COMP_REGEX​

const TWO_COMP_REGEX: RegExp;

Defined in: packages/ai-research-agent/src/extractor/html-to-cite/extract-date/date-extractors.js:85


discard_unwanted()​

function discard_unwanted(tree: any): any[];

Defined in: packages/ai-research-agent/src/extractor/html-to-cite/extract-date/date-extractors.js:186

Parameters​

ParameterType

tree

any

Returns​

any[]


extract_url_date()​

function extract_url_date(testurl: any, options: any): string;

Defined in: packages/ai-research-agent/src/extractor/html-to-cite/extract-date/date-extractors.js:196

Parameters​

ParameterType

testurl

any

options

any

Returns​

string


regex_parse()​

function regex_parse(string: any): Date;

Defined in: packages/ai-research-agent/src/extractor/html-to-cite/extract-date/date-extractors.js:225

Parameters​

ParameterType

string

any

Returns​

Date


custom_parse()​

function custom_parse(
string: any,
outputformat: any,
min_date: any,
max_date: any): string;

Defined in: packages/ai-research-agent/src/extractor/html-to-cite/extract-date/date-extractors.js:247

Parameters​

ParameterType

string

any

outputformat

any

min_date

any

max_date

any

Returns​

string


external_date_parser()​

function external_date_parser(string: any, outputformat: any): string;

Defined in: packages/ai-research-agent/src/extractor/html-to-cite/extract-date/date-extractors.js:342

Parameters​

ParameterType

string

any

outputformat

any

Returns​

string


try_date_expr()​

function try_date_expr(
string: any,
outputformat: any,
extensive_search: any,
min_date: any,
max_date: any): string;

Defined in: packages/ai-research-agent/src/extractor/html-to-cite/extract-date/date-extractors.js:356

Parameters​

ParameterType

string

any

outputformat

any

extensive_search

any

min_date

any

max_date

any

Returns​

string


function img_search(tree: any, options: any): string;

Defined in: packages/ai-research-agent/src/extractor/html-to-cite/extract-date/date-extractors.js:386

Parameters​

ParameterType

tree

any

options

any

Returns​

string


function pattern_search(
text: any,
date_pattern: any,
options: any): any;

Defined in: packages/ai-research-agent/src/extractor/html-to-cite/extract-date/date-extractors.js:394

Parameters​

ParameterType

text

any

date_pattern

any

options

any

Returns​

any


function json_search(tree: any, options: any): any;

Defined in: packages/ai-research-agent/src/extractor/html-to-cite/extract-date/date-extractors.js:403

Parameters​

ParameterType

tree

any

options

any

Returns​

any


function idiosyncrasies_search(htmlstring: any, options: any): string;

Defined in: packages/ai-research-agent/src/extractor/html-to-cite/extract-date/date-extractors.js:416

Parameters​

ParameterType

htmlstring

any

options

any

Returns​

string