joshlaymon/Illustrations
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Update web/core/scripture_normalizer.py

Browse Source
This commit is contained in:
Joshua Laymon 2025-08-14 01:54:21 +00:00
parent 260d70f4cd
commit a461cd1bc7
1 changed files with 89 additions and 89 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

172
web/core/scripture_normalizer.py
View File

@ -4,117 +4,124 @@ import re
from typing import Dict, List, Tuple from typing import Dict, List, Tuple
# --- Book map (common full names + abbreviations -> canonical abbr) --- # --- Book map (common full names + abbreviations -> canonical abbr) ---
# Tweak any canonical value if you prefer a different house style.
BOOK_CANON = { BOOK_CANON = {
# OT # OT
"genesis": "Gen.", "gen": "Gen.", "genesisesis": "Gen.", "genesis": "Gen.", "gen": "Gen.", "genesisesis": "Gen.", "genesis sis": "Gen.", "ge": "Gen.",
"exodus": "Ex.", "ex": "Ex.", "exodus": "Ex.", "ex": "Ex.", "exo": "Ex.", "exod": "Ex.", "exodus.": "Ex.",
"leviticus": "Lev.", "lev": "Lev.", "leviticus": "Lev.", "lev": "Lev.", "le": "Lev.",
"numbers": "Num.", "num": "Num.", "nums": "Num.", "numbers": "Num.", "num": "Num.", "nums": "Num.", "nu": "Num.",
"deuteronomy": "Deut.", "deut": "Deut.", "deu": "Deut.", "deutronomy": "Deut.", "deut.": "Deut.", "deuteronomy": "Deut.", "deut": "Deut.", "deu": "Deut.", "de": "Deut.", "deutronomy": "Deut.", "deut.": "Deut.",
"joshua": "Josh.", "josh": "Josh.", "joshua": "Josh.", "josh": "Josh.", "jos": "Josh.",
"judges": "Judg.", "judg": "Judg.", "judges": "Judg.", "judg": "Judg.", "judg.": "Judg.", "judg": "Judg.",
"ruth": "Ruth", "ruth": "Ruth",
"1 samuel": "1 Sam.", "i samuel": "1 Sam.", "1 sam": "1 Sam.", "1 samuel": "1 Sam.", "i samuel": "1 Sam.", "1 sam": "1 Sam.", "1sa": "1 Sam.",
"2 samuel": "2 Sam.", "ii samuel": "2 Sam.", "2 sam": "2 Sam.", "2 samuel": "2 Sam.", "ii samuel": "2 Sam.", "2 sam": "2 Sam.", "2sa": "2 Sam.",
"1 kings": "1 Ki.", "i kings": "1 Ki.", "1 ki": "1 Ki.", "1kgs": "1 Ki.", "1 kgs": "1 Ki.", "1 kings": "1 Ki.", "i kings": "1 Ki.", "1 ki": "1 Ki.", "1kgs": "1 Ki.", "1 kgs": "1 Ki.", "1ki": "1 Ki.",
"2 kings": "2 Ki.", "ii kings": "2 Ki.", "2 ki": "2 Ki.", "2kgs": "2 Ki.", "2 kgs": "2 Ki.", "2 kings": "2 Ki.", "ii kings": "2 Ki.", "2 ki": "2 Ki.", "2kgs": "2 Ki.", "2 kgs": "2 Ki.", "2ki": "2 Ki.",
"1 chronicles": "1 Chron.", "i chronicles": "1 Chron.", "1 chron": "1 Chron.", "1 chronicles": "1 Chron.", "i chronicles": "1 Chron.", "1 chron": "1 Chron.", "1 ch": "1 Chron.", "1ch": "1 Chron.",
"2 chronicles": "2 Chron.", "ii chronicles": "2 Chron.", "2 chron": "2 Chron.", "2 chronicles": "2 Chron.", "ii chronicles": "2 Chron.", "2 chron": "2 Chron.", "2 ch": "2 Chron.", "2ch": "2 Chron.",
"ezra": "Ezra", "ezra": "Ezra",
"nehemiah": "Neh.", "neh": "Neh.", "nehemiah": "Neh.", "neh": "Neh.", "ne": "Neh.",
"esther": "Esth.", "esth": "Esth.", "esther": "Esth.", "esth": "Esth.",
"job": "Job", "job": "Job",
"psalm": "Ps.", "psalms": "Ps.", "ps": "Ps.", "psa": "Ps.", "psalm": "Ps.", "psalms": "Ps.", "ps": "Ps.", "ps.": "Ps.", "pss": "Ps.",
"proverbs": "Prov.", "prov": "Prov.", "proverbs": "Prov.", "prov": "Prov.", "prov.": "Prov.", "pr": "Prov.",
"ecclesiastes": "Eccl.", "eccles": "Eccl.", "eccl": "Eccl.", "ecclesiastes": "Eccl.", "eccles": "Eccl.", "eccl": "Eccl.", "ecclesiastes.": "Eccl.", "ecc": "Eccl.", "ec": "Eccl.",
"song of solomon": "Song", "song of songs": "Song", "song": "Song", "song of solomon": "Song", "song of songs": "Song", "song": "Song",
"isaiah": "Isa.", "isa": "Isa.", "isaiah": "Isa.", "isa": "Isa.", "is": "Isa.",
"jeremiah": "Jer.", "jer": "Jer.", "jer.": "Jer.", "jeremiah": "Jer.", "jer": "Jer.", "jer.": "Jer.", "je": "Jer.",
"lamentations": "Lam.", "lam": "Lam.", "lamentations": "Lam.", "lam": "Lam.", "la": "Lam.",
"ezekiel": "Ezek.", "ezek": "Ezek.", "ezekiel": "Ezek.", "ezek": "Ezek.", "eze": "Ezek.",
"daniel": "Dan.", "dan": "Dan.", "daniel": "Dan.", "dan": "Dan.", "da": "Dan.",
"hosea": "Hos.", "hos": "Hos.", "hosea": "Hos.", "hos": "Hos.", "ho": "Hos.",
"joel": "Joel", "joel": "Joel",
"amos": "Amos", "amos": "Amos",
"obadiah": "Obad.", "obad": "Obad.", "obadiah": "Obad.", "obad": "Obad.",
"jonah": "Jon.", "jon": "Jon.", "jonah": "Jon.", "jon": "Jon.",
"micah": "Mic.", "mic": "Mic.", "micah": "Mic.", "mic": "Mic.",
"nahum": "Nah.", "nah": "Nah.", "nahum": "Nah.", "nah": "Nah.", "na": "Nah.",
"habakkuk": "Hab.", "hab": "Hab.", "habakkuk": "Hab.", "hab": "Hab.",
"zephaniah": "Zeph.", "zeph": "Zeph.", "zephaniah": "Zeph.", "zeph": "Zeph.",
"haggai": "Hag.", "hag": "Hag.", "haggai": "Hag.", "hag": "Hag.",
"zechariah": "Zech.", "zech": "Zech.", "zechariah": "Zech.", "zech": "Zech.", "zec": "Zech.",
"malachi": "Mal.", "mal": "Mal.", "malachi": "Mal.", "mal": "Mal.",
# NT # NT
"matthew": "Matt.", "matt": "Matt.", "mt": "Matt.", "matthew": "Matt.", "matt": "Matt.", "mt": "Matt.", "mt.": "Matt.",
"mark": "Mark", "mk": "Mark", "mark": "Mark", "mk": "Mark", "mr": "Mark", "mr.": "Mark",
"luke": "Luke", "lk": "Luke", "luke": "Luke", "lk": "Luke", "lu": "Luke",
"john": "John", "jn": "John", "john": "John", "jn": "John", "joh": "John", "jno": "John", "jo": "John",
"acts": "Acts", "acts": "Acts", "ac": "Acts",
"romans": "Rom.", "rom": "Rom.", "romans": "Rom.", "rom": "Rom.", "ro": "Rom.",
"1 corinthians": "1 Cor.", "i corinthians": "1 Cor.", "1 cor": "1 Cor.", "1 cor.": "1 Cor.", "1 corinthians": "1 Cor.", "i corinthians": "1 Cor.", "1 cor": "1 Cor.", "1 cor.": "1 Cor.", "1 co": "1 Cor.", "1co": "1 Cor.",
"2 corinthians": "2 Cor.", "ii corinthians": "2 Cor.", "2 cor": "2 Cor.", "2 cor.": "2 Cor.", "2 corinthians": "2 Cor.", "ii corinthians": "2 Cor.", "2 cor": "2 Cor.", "2 cor.": "2 Cor.", "2 co": "2 Cor.", "2co": "2 Cor.",
"galatians": "Gal.", "gal": "Gal.", # bare "co" (no leading number) is used in your data for Colossians; keep that mapping here:
"ephesians": "Eph.", "eph": "Eph.", "eph.": "Eph.", "co": "Col.",
"philippians": "Phil.", "phil": "Phil.", "philippians 216": "Phil.", # common import glitch "galatians": "Gal.", "gal": "Gal.", "ga": "Gal.",
"ephesians": "Eph.", "eph": "Eph.", "ep": "Eph.", "eph.": "Eph.",
"philippians": "Phil.", "phil": "Phil.", "php": "Phil.", "philippians 216": "Phil.", # import glitch
"colossians": "Col.", "col": "Col.", "colossians": "Col.", "col": "Col.",
"1 thessalonians": "1 Thess.", "i thessalonians": "1 Thess.", "1 thess": "1 Thess.", "1 thes": "1 Thess.", "1 thessalonians": "1 Thess.", "i thessalonians": "1 Thess.", "1 thess": "1 Thess.", "1th": "1 Thess.",
"2 thessalonians": "2 Thess.", "ii thessalonians": "2 Thess.", "2 thess": "2 Thess.", "2 thes": "2 Thess.", "2 thessalonians": "2 Thess.", "ii thessalonians": "2 Thess.", "2 thess": "2 Thess.", "2th": "2 Thess.",
"1 timothy": "1 Tim.", "i timothy": "1 Tim.", "1 tim": "1 Tim.", "1ti": "1 Tim.", "1 timothy": "1 Tim.", "i timothy": "1 Tim.", "1 tim": "1 Tim.", "1ti": "1 Tim.",
"2 timothy": "2 Tim.", "ii timothy": "2 Tim.", "2 tim": "2 Tim.", "2ti": "2 Tim.", "2 timothy": "2 Tim.", "ii timothy": "2 Tim.", "2 tim": "2 Tim.", "2ti": "2 Tim.",
"titus": "Titus", "ti": "Tim.", # 'Ti' is usually Timothy in your data "ti": "Tim.", # context handles numbered elsewhere
"philemon": "Philem.", "philem": "Philem.", "titus": "Titus", "tit": "Titus",
"hebrews": "Heb.", "heb": "Heb.", "philemon": "Philem.", "philem": "Philem.", "phm": "Philem.",
"james": "Jas.", "jas": "Jas.", "hebrews": "Heb.", "heb": "Heb.", "he": "Heb.",
"1 peter": "1 Pet.", "i peter": "1 Pet.", "1 pet": "1 Pet.", "james": "Jas.", "jas": "Jas.", "jam": "Jas.",
"2 peter": "2 Pet.", "ii peter": "2 Pet.", "2 pet": "2 Pet.", "1 peter": "1 Pet.", "i peter": "1 Pet.", "1 pet": "1 Pet.", "1pe": "1 Pet.",
"1 john": "1 John", "i john": "1 John", "2 peter": "2 Pet.", "ii peter": "2 Pet.", "2 pet": "2 Pet.", "2pe": "2 Pet.",
"2 john": "2 John", "ii john": "2 John", "1 john": "1 John", "i john": "1 John", "1 jn": "1 John", "1 jo": "1 John", "1jo": "1 John",
"3 john": "3 John", "iii john": "3 John", "2 john": "2 John", "ii john": "2 John", "2 jn": "2 John", "2jo": "2 John",
"3 john": "3 John", "iii john": "3 John", "3 jn": "3 John", "3jo": "3 John",
"jude": "Jude", "jude": "Jude",
"revelation": "Rev.", "rev": "Rev.", "revelation": "Rev.", "rev": "Rev.", "re": "Rev.",
# very short generic stems
"cor": "Cor.", "co": "Cor.",
"thess": "Thess.", "thes": "Thess.",
} }
# add “numbered+book” fallbacks like “1 cor”, “2 ki”, “1 chron”, etc.
def _variants() -> Dict[str, str]: def _variants() -> Dict[str, str]:
"""
Add “numbered + book” fallbacks like “1 cor”, “2 ki”, “1 chron”, etc.
Also teach the mapper that bare 'co' (no number) means Colossians, while '1co/2co' means Corinthians.
"""
base = dict(BOOK_CANON) base = dict(BOOK_CANON)
numbered = [ numbered = [
("samuel", "Sam."), ("kings", "Ki."), ("chronicles", "Chron."), ("samuel", "Sam."), ("kings", "Ki."), ("chronicles", "Chron."),
("corinthians", "Cor."), ("cor", "Cor."), ("co", "Cor."), ("corinthians", "Cor."), ("thessalonians", "Thess."),
("thessalonians", "Thess."), ("thess", "Thess."), ("thes", "Thess."), ("timothy", "Tim."), ("peter", "Pet."), ("john", "John"),
("timothy", "Tim."), ("ti", "Tim."),
("peter", "Pet."), ("john", "John"),
] ]
for n in ("1", "i"): for n in ("1", "i"):
for name, abbr in numbered: for name, abbr in numbered:
base[f"{n} {name}"] = f"1 {abbr}" base[f"{n} {name}"] = f"1 {abbr}"
base[f"{n}{name}"] = f"1 {abbr}" # very short glued forms used in the data (no space):
base[f"{n}ki"] = "1 Ki."
base[f"{n}ch"] = "1 Chron."
base[f"{n}co"] = "1 Cor."
base[f"{n}jo"] = "1 John"
for n in ("2", "ii"): for n in ("2", "ii"):
for name, abbr in numbered: for name, abbr in numbered:
base[f"{n} {name}"] = f"2 {abbr}" base[f"{n} {name}"] = f"2 {abbr}"
base[f"{n}{name}"] = f"2 {abbr}" base[f"{n}ki"] = "2 Ki."
base[f"{n}ch"] = "2 Chron."
base[f"{n}co"] = "2 Cor."
base[f"{n}jo"] = "2 John"
for n in ("3", "iii"): for n in ("3", "iii"):
base[f"{n} john"] = "3 John" base[f"{n} john"] = "3 John"
base[f"{n}john"] = "3 John" base[f"{n}jo"] = "3 John"
# very common shorthands
# other common shorthands / oddities
base["ps"] = "Ps." base["ps"] = "Ps."
base["prov"] = "Prov." base["prov"] = "Prov."
base["pr"] = "Prov."
base["eccles"] = "Eccl." base["eccles"] = "Eccl."
base["ecc"] = "Eccl."
base["ec"] = "Eccl."
base["deut "] = "Deut." base["deut "] = "Deut."
base["deut."] = "Deut." base["deut."] = "Deut."
base["genesissis"] = "Gen."
return base return base
BOOK_MAP = _variants() BOOK_MAP = _variants()
# Extra explicit short forms that don't naturally fall out of the variant builder.
BOOK_MAP.update({
"1 co": "1 Cor.", "2 co": "2 Cor.", "1co": "1 Cor.", "2co": "2 Cor.",
})
# strip cruft words like "Read", "chapter" # strip cruft words like "Read", "chapter"
CRUFT_RE = re.compile(r"\b(read|see|chap(?:ter)?|ch)\b\.?", re.I) CRUFT_RE = re.compile(r"\b(read|see|chap(?:ter)?|ch)\b\.?", re.I)
@ -123,7 +130,7 @@ BOOK_RE = re.compile(
r""" r"""
^\s* ^\s*
(?: (?:
(?P<num>[1-3]|i{1,3})\s* # optional leading 1/2/3 (or roman i/ii/iii) (?P<num>[1-3]|i{1,3})\s*? # optional leading 1/2/3 (or roman i/ii/iii)
)? )?
\s* \s*
(?P<book>[A-Za-z\.]+(?:\s+[A-Za-z\.]+){0,2}) # book words (1-3 words) (?P<book>[A-Za-z\.]+(?:\s+[A-Za-z\.]+){0,2}) # book words (1-3 words)
@ -145,26 +152,27 @@ C_V_RE = re.compile(
re.X re.X
) )
def _clean_text(s: str) -> str: def _clean_text(s: str) -> str:
s = s.replace("\xa0", " ").replace("\u2009", " ").replace("\u202f", " ") s = s.replace("\xa0", " ").replace("\u2009", " ").replace("\u202f", " ")
s = CRUFT_RE.sub("", s) s = CRUFT_RE.sub("", s)
s = s.replace("..", ".").replace("—", "-").replace("–", "-") s = s.replace("..", ".").replace("—", "-").replace("–", "-")
s = s.replace(" ", " ").strip(" ;,.\t\r\n") s = s.replace(" ", " ").strip(" ;,.\t\r\n")
# NEW: if entry begins with a number stuck to the book (e.g., "1co", "2ki"), insert a space
s = re.sub(r"^\s*(?P<num>(?:[1-3]|i{1,3}))(?=[A-Za-z])", r"\g<num> ", s, flags=re.I)
return s.strip() return s.strip()
def _canon_book(book_raw: str) -> str | None: def _canon_book(book_raw: str) -> str | None:
if not book_raw: if not book_raw:
return None return None
key = book_raw.lower().strip().replace(".", "") key = book_raw.lower().strip().replace(".", "")
key = re.sub(r"\s+", " ", key) key = re.sub(r"\s+", " ", key)
# allow glued forms (e.g., "1co", "2ki", "1ch")
key = re.sub(r"^(?P<num>(?:[1-3]|i{1,3}))(?=[a-z])", r"\g<num> ", key)
# try exact # try exact
if key in BOOK_MAP: if key in BOOK_MAP:
return BOOK_MAP[key] return BOOK_MAP[key]
# try adding number + name variants already in map # finally, try canonical map without variants
return BOOK_CANON.get(key) # last-resort return BOOK_CANON.get(key)
def _parse_segment(seg: str, last_book: str | None) -> Tuple[str | None, str | None]: def _parse_segment(seg: str, last_book: str | None) -> Tuple[str | None, str | None]:
""" """
@ -190,26 +198,22 @@ def _parse_segment(seg: str, last_book: str | None) -> Tuple[str | None, str | N
rest = s rest = s
if not book: if not book:
book = last_book # inherit prior (e.g., "14:20" after "1 Cor. 13:11") book = last_book # inherit prior
# now rest should hold "4:6,7-9" or "21" etc — normalize spaces # now rest should hold "4:6,7-9" or "21" etc — normalize spaces
rest = re.sub(r"\s+", "", rest) rest = rest.replace(" ", "")
rest = re.sub(r":\s+", ":", rest) # "2: 24" -> "2:24" rest = re.sub(r":\s+", ":", rest)
# allow chapter-only
if not rest: if not rest:
cv = None cv = None
else: else:
if C_V_RE.search(rest): if C_V_RE.search(rest):
cv = rest cv = rest.replace(" ", "")
# normalize commas to include a following space: "6,7" -> "6, 7"
cv = re.sub(r"\s*,\s*", ", ", cv)
else: else:
m2 = re.search(r"\d+(?::[\d,\-]+)?", rest) m2 = re.search(r"\d+(?::[\d,\-]+)?", rest)
cv = re.sub(r"\s*,\s*", ", ", m2.group(0)) if m2 else None cv = m2.group(0).replace(" ", "") if m2 else None
return (book, cv) return (book, cv)
def normalize_scripture_field(text: str) -> Tuple[str, List[str]]: def normalize_scripture_field(text: str) -> Tuple[str, List[str]]:
""" """
Normalize a whole scripture_raw string. Normalize a whole scripture_raw string.
@ -219,7 +223,6 @@ def normalize_scripture_field(text: str) -> Tuple[str, List[str]]:
if not text: if not text:
return ("", warnings) return ("", warnings)
# split on semicolons; keep empty pieces out
pieces = [p for p in re.split(r"\s*;\s*", text) if p and p.strip()] pieces = [p for p in re.split(r"\s*;\s*", text) if p and p.strip()]
out: List[str] = [] out: List[str] = []
last_book: str | None = None last_book: str | None = None
@ -232,15 +235,12 @@ def normalize_scripture_field(text: str) -> Tuple[str, List[str]]:
out.append(book) out.append(book)
last_book = book last_book = book
continue continue
if not book and cv: if not book and cv:
warnings.append(f"Missing book for '{piece.strip()}'") warnings.append(f"Missing book for '{piece.strip()}'")
continue continue
cv = (cv or "").replace("–", "-").replace("—", "-") cv = (cv or "").replace("–", "-").replace("—", "-")
cv = re.sub(r"\s+", " ", cv).strip() out.append(f"{book} {cv}")
out.append(f"{book} {cv}" if cv else f"{book}")
last_book = book last_book = book
norm = "; ".join(o.strip() for o in out if o.strip()) norm = "; ".join(o.strip() for o in out if o.strip())