#!/usr/bin/env python3
"""Derive lectio's Greek corpus from upstream grb (github.com/lukesmithxyz/grb).

Upstream grb is a standalone reader and carries the whole Septuagint -- 87
books, including manuscript variants and books with no Vulgate counterpart.
lectio needs one uniform canon: the 73 books vul has, under vul's names. So
this filters rather than forks, and upstream stays untouched.

Five books ARE in the Vulgate canon but appear under other names, and the
verse counts confirm which witness the Vulgate follows -- Jerome translated
Theodotion, not the Old Greek:

    Bel and the Dragon (Theodotion)  42 verses = vul Daniel 14   (42)  exact
    Bel and the Dragon (LXX)         37 verses                          no
    Sussana (Theodotion)             64 verses = vul Daniel 13   (65)
    Sussana (LXX)                    37 verses                          no
    Letter of Jeremiah               73 verses = vul Baruch 6    (72)
    Wisdom of Solomon               435 verses = vul Wisdom     (439)

Upstream's plain "Daniel" is the Old Greek AND is missing chapter 4 outright
(it has 1,2,3,5..12), so Theodotion supplies Daniel throughout: complete, and
the tradition the Vulgate and the lectionary actually use.

Two upstream defects are repaired on the way through:

  * 408 rows carry 5 fields, not 6: a lost tab fused the book number and the
    chapter into one token ("281" = book 28, chapter 1). Every one is in Hosea
    or Zechariah, and neither book has a single well-formed row -- bible.go
    skips rows that are not exactly 6 fields, so both books were absent from
    lectio at runtime with no error and no warning.
  * The first row's book name carries a UTF-8 BOM, making "Genesis" a 74th
    book that matches nothing.

From the repo root:
    python3 scripts/gen-grb-lectio.py            # report only
    python3 scripts/gen-grb-lectio.py --write    # rewrite the corpus
"""
import collections
import os
import re
import sys

ROOT = os.path.dirname(os.path.dirname(os.path.abspath(__file__)))
UPSTREAM = os.environ.get("GRB_TSV", os.path.expanduser("~/git/grb/grb.tsv"))
OUT = os.path.join(ROOT, "internal", "bible", "corpora_optional", "grb.tsv")
SCHEMA = os.path.join(ROOT, "internal", "bible", "corpora_optional", "wuj.tsv")

# fused book number + chapter; both books have 14 chapters
FUSED = {"Hosea": 28, "Zechariah": 38}
MAXCH = 14

# book -> (canonical name, forced chapter or None)
REMAP = {
    "Daniel (Theodotion)": ("Daniel", None),
    "Sussana (Theodotion)": ("Daniel", 13),
    "Bel and the Dragon (Theodotion)": ("Daniel", 14),
    "Letter of Jeremiah": ("Baruch", 6),
    "Wisdom of Solomon": ("Wisdom", None),
}

DROP = {
    "Daniel",                      # Old Greek, and missing chapter 4
    "Sussana", "Bel and the Dragon",
    "Judges (Vaticanus)", "Tobit (Sinaiticus)",
    "1 Esdras", "2 Esdras", "3 Maccabees", "4 Maccabees",
    "Odes", "Psalms of Solomon",
}


def schema():
    """canonical (number, abbrev) per book name, from an existing corpus."""
    out = {}
    for line in open(SCHEMA, encoding="utf-8"):
        f = line.rstrip("\n").split("\t")
        if len(f) == 6 and f[0] not in out:
            out[f[0]] = (f[2], f[1])
    return out


# SBLGNT critical-apparatus sigla, e.g. "⸀μαθητάς" or a "⸂...⸃" bracketed
# variant. They are editorial marks on the text, not the text, and
# TestGrbNoApparatusMarkers guards their absence -- regenerating from raw
# upstream reintroduces roughly 8700 of them.
APPARATUS = re.compile(r"[⸀-⸍]")


def strip_apparatus(s):
    return re.sub(r"\s{2,}", " ", APPARATUS.sub("", s)).strip()


def read_upstream():
    rows, repaired, ranges, dropped_bad = [], 0, 0, 0
    for line in open(UPSTREAM, encoding="utf-8"):
        f = line.rstrip("\n").split("\t")
        if f:
            f[0] = f[0].lstrip("")
        if len(f) >= 5:
            f[-1] = strip_apparatus(f[-1])

        if len(f) == 5:
            book, abbr, fused, verse, text = f
            nr = FUSED.get(book)
            if nr and fused.startswith(str(nr)):
                ch = fused[len(str(nr)):]
                if ch.isdigit() and 1 <= int(ch) <= MAXCH:
                    rows.append([book, abbr, str(nr), ch, verse, text])
                    repaired += 1
                    continue
            dropped_bad += 1
            continue

        if len(f) != 6:
            dropped_bad += 1
            continue

        if not f[4].isdigit():                 # merged label like "27-28"
            m = re.match(r"(\d+)", f[4])
            if not m:
                dropped_bad += 1
                continue
            f[4] = m.group(1)
            ranges += 1
        rows.append(f)
    return rows, repaired, ranges, dropped_bad


def main():
    if not os.path.exists(UPSTREAM):
        sys.exit("upstream grb.tsv not found at %s (set GRB_TSV)" % UPSTREAM)

    rows, repaired, ranges, bad = read_upstream()
    canon = schema()

    kept, dropped = [], collections.Counter()
    for r in rows:
        book = r[0]
        if book in DROP:
            dropped[book] += 1
            continue
        if book in REMAP:
            book, forced = REMAP[book]
            r[0] = book
            if forced is not None:
                r[3] = str(forced)
        if book not in canon:
            dropped[book] += 1
            continue
        r[2], r[1] = canon[book][0], r[1]
        kept.append(r)

    kept.sort(key=lambda r: (int(r[2]), int(r[3]), int(r[4])))

    books = {r[0] for r in kept}
    print("upstream rows repaired (fused column) : %d" % repaired)
    print("merged verse labels normalised        : %d" % ranges)
    print("unusable rows discarded               : %d" % bad)
    print("books dropped (outside vul canon)     : %d" % len(dropped))
    for b, n in sorted(dropped.items(), key=lambda kv: -kv[1]):
        print("    %-34s %5d verses" % (b, n))
    print("books kept                            : %d" % len(books))
    print("rows kept                             : %d" % len(kept))
    missing = sorted(set(canon) - books)
    if missing:
        print("canonical books with no Greek text    : %s" % ", ".join(missing))

    if "--write" not in sys.argv[1:]:
        print("\nnot written; pass --write to rewrite %s" % OUT)
        return
    with open(OUT, "w", encoding="utf-8") as f:
        for r in kept:
            f.write("\t".join(r) + "\n")
    print("\nwrote %s" % OUT)


main()