regexes.json

{
    "full_cite": {
        "": "$volume $reporter,? $page",
        "#": "Standard citation",
        "cch": "(?:$volume_with_digit_suffix )?$full_cite_paragraph",
        "cch#": "Cite in CCH service format, like '1982-1 Trade Cas. (CCH) par. 64,689'",
        "cch_suffix": "(?:$volume_with_digit_suffix )?$full_cite_paragraph_with_suffix",
        "cch_suffix#": "Cite in CCH service format with suffix, like 'Pens. Plan Guide (CCH) P 24014F'",
        "format_neutral": {
            "": "$volume_year\\s?-?$reporter-?\\s?$page",
            "#": "Format neutral cite, like '2000-Ohio-123' or '2014 -Ohio- 566' or '2000 NMCA 69'",
            "3_4": "$volume_year\\s?-$reporter-\\s?$page_3_4",
            "3_4#": "Format neutral cite where the page must be 3 or 4 digits, like '2000-NMSC-123' or '2009 -NMSC- 034'"
        },
        "illinois_neutral": {
            "": "$volume_year $reporter (?P<page>\\d{6}(?:-?[A-Z]|WC)?)",
            "#": "Illinois format-neutral cite with an optional -letter in page number."
        },
        "louisiana": {
            "": "(?P<volume>\\d{2,4})[- ](?P<page>\\d{2,5}[A-Z]?) \\($reporter (?P<date_filed>\\d{1,2}\\/\\d{1,2}\\/\\d{2,4})\\)",
            "#": "Format neutral Louisiana cite, like '2009 1359R (La.App. 1 Cir. 05/10/10)'"
        },
        "paragraph": {
            "": "$reporter $paragraph_marker_optional$page_with_commas",
            "#": "Citation to a paragraph instead of a volume, like 'Bankr. L. Rep. ¶12,345'",
            "with_suffix": "$reporter $paragraph_marker_optional$page_with_commas_and_suffix",
            "with_suffix#": "Paragraph cite with optional alpha character appended"
        },
        "single_volume": "(?:(?P<volume>1) )?$reporter $page",
        "year_included": {
            "": "$volume $reporter \\((?P<year>1[789]\\d{2}|20\\d{2}),?\\) $page",
            "#": "Citation that includes the volume year after the reporter '14 Haz. Reg. Pa. (1834) 10'"
        },
        "year_page": "$reporter $volume_year-$page"
    },
    "law": {
        "#": "Regexes used in laws.json",
        "day": "(?P<day>\\d{1,2}),?",
        "month": "(?P<month>[A-Z][a-z]+\\.?)",
        "section": "(?P<section>\\d+(?:[\\-.:]\\d+){,3})",
        "section#": "Section like 1-2-3, 1.2.3, or 1:2-3.4",
        "subject": "(?P<subject>$law_subject_word(?: $law_subject_word| &){,4})",
        "subject#": "One to five word statute subject like 'Parks Rec. & Hist. Preserv.', 'Not-for-Profit Corp.', 'Alt. County Gov’t', 'R.R.'",
        "subject_word": "[A-Z][.\\-'A-Za-z]*",
        "subject_word#": "Single word in statute subject, like Rec., Gov't, or Not-for-Profit",
        "year": "(?P<year>1\\d{3}|20\\d{2})"
    },
    "page": {
        "": "(?P<page>\\d+)",
        "#": "Standard page number",
        "3_4": "(?P<page>\\d{3,4})",
        "3_4#": "Page number that must be 3 or 4 digits long",
        "with_commas": "(?P<page>\\d(?:[\\d,]*\\d)?)",
        "with_commas#": "Page number that allows internal commas, like '12,345,678'. Doesn't enforce 3-digit groups.",
        "with_commas_and_suffix": "(?P<page>\\d(?:[\\d,]*\\d)?[A-Z]?)",
        "with_commas_and_suffix#": "Page number that allows internal commas, plus optional alpha character appended",
        "with_commas_or_periods": "(?P<page>\\d(?:[\\d,.]*\\d)?)",
        "with_commas_or_periods#": "Page number that allows internal punctuation",
        "with_letter": "(?P<page>\\d+[a-zA-Z]+)",
        "with_letter#": "Page number followed by a letter",
        "with_periods": "(?P<page>\\d(?:[\\d.]*\\d)?)",
        "with_periods#": "Page number that allows internal periods, like '1234.56'",
        "with_roman_numerals": "(?P<page>[cC]?(?:[xX][cC]|[xX][lL]|[lL]?[xX]{1,3})(?:[iI][xX]|[iI][vV]|[vV]?[iI]{0,3})|(?:[cC]?[lL]?)(?:[iI][xX]|[iI][vV]|[vV]?[iI]{1,3})|(?:[lL][vV]|[cC][vV]|[cC][lL]|[cC][lL][vV]))",
        "with_roman_numerals#": "Page number expressed as Roman numerals"
    },
    "paragraph_marker": "(?:P|P.|¶|Paragraph|at|para?\\.)",
    "reporter": {
        "": "(?P<reporter>$edition)",
        "#": "Standard reporter"
    },
    "section_marker": "((§§?)|([Ss]((ec)(tion)?)?s?\\.?))",
    "volume": {
        "": "(?P<volume>\\d+)",
        "#": "Standard volume number",
        "nominative": "(?:(?P<volume_nominative>\\d{1,2}) )?",
        "nominative#": "Nominative volume number embedded in an official cite; made optional for single-volume nominatives",
        "with_alpha_suffix": "(?P<volume>\\d{1,4}A?)",
        "with_alpha_suffix#": "Volume number that may have 'A' appended, like '1A'",
        "with_digit_suffix": "(?P<volume>\\d{1,4}(?:-\\d+)?)",
        "with_digit_suffix#": "Volume number that may have digits appended, like '123-4'",
        "with_letter": "(?P<volume>\\d+[a-zA-Z])",
        "with_letter#": "Volume number followed by a letter",
        "year": "(?P<volume>1[789]\\d{2}|20\\d{2})",
        "year#": "Volume number that must be a year between 1900 and 2099"
    }
}