着想から運用までの通し手順── Word 文書の表記点検を例に、着想から保守までを 1 本で

python -m venv .venv
.venv\Scripts\Activate.ps1
python -m pip install python-docx==1.2.0
python -m pip freeze > requirements.txt

"""Check .docx files in a folder against a style list and write the hits to a CSV file.

usage: python check_terms.py DOCS_FOLDER TERMS_CSV OUT_CSV
"""
import csv
import re
import sys
import unicodedata
from collections import Counter
from dataclasses import dataclass
from pathlib import Path

from docx import Document

SENTENCE_END = re.compile(r"(?<=[。！？!?])")


@dataclass(frozen=True)
class Term:
    term: str
    category: str
    action: str
    key: str


@dataclass(frozen=True)
class Hit:
    file: str
    where: str
    term: str
    action: str
    sentence: str


def normalize(text):
    # NFKC turns full-width letters and digits into their usual forms; casefold ignores case
    return unicodedata.normalize("NFKC", text).casefold()


def load_terms(path):
    with open(path, encoding="utf-8-sig", newline="") as f:
        return [Term(r["term"], r["category"], r["action"], normalize(r["term"]))
                for r in csv.DictReader(f) if r["term"].strip()]


def iter_blocks(doc):
    for i, p in enumerate(doc.paragraphs, 1):
        yield "paragraph %d" % i, p.text
    for ti, table in enumerate(doc.tables, 1):
        for ri, row in enumerate(table.rows, 1):
            for ci, cell in enumerate(row.cells, 1):
                yield "table %d row %d col %d" % (ti, ri, ci), cell.text


def split_sentences(text):
    return [s.strip() for s in SENTENCE_END.split(text) if s.strip()]


def find_hits(name, where, sentence, terms):
    key = normalize(sentence)
    return [Hit(name, where, t.term, t.action, sentence) for t in terms if t.key in key]


def check_folder(folder, terms):
    hits = []
    for path in sorted(Path(folder).glob("*.docx")):
        if path.name.startswith("~$"):
            continue  # lock files that Word leaves while a document is open
        for where, text in iter_blocks(Document(path)):
            for sentence in split_sentences(text):
                hits += find_hits(path.name, where, sentence, terms)
    return hits


def write_csv(hits, out):
    with open(out, "w", encoding="utf-8-sig", newline="") as f:
        w = csv.writer(f)
        w.writerow(["file", "where", "term", "action", "sentence"])
        w.writerows([h.file, h.where, h.term, h.action, h.sentence] for h in hits)


def main(folder, terms_csv, out_csv):
    hits = check_folder(folder, load_terms(terms_csv))
    write_csv(hits, out_csv)
    print("hits:", len(hits))
    for name, n in sorted(Counter(h.file for h in hits).items()):
        print(" ", name, n)
    for h in hits[:8]:
        print("  %s | %s | %s -> %s" % (h.file, h.where, h.term, h.action))


if __name__ == "__main__":
    main(*(sys.argv[1:] or ["samples", "samples/style_terms.csv", "out_hits.csv"]))

"""Tests for check_terms.py (run: python test_check_terms.py)."""
import sys
import unittest

from check_terms import Term, check_folder, find_hits, load_terms, normalize, split_sentences

TERMS = [Term("No.1", "順位の表現", "出典を併記する", normalize("No.1")),
         Term("下さい", "表記ゆれ", "「ください」に統一", normalize("下さい"))]


class CheckTermsTest(unittest.TestCase):
    def test_full_width_matches(self):
        hits = find_hits("a.docx", "paragraph 1", "満足度Ｎｏ．１です。", TERMS)
        self.assertEqual([h.term for h in hits], ["No.1"])

    def test_rewritten_sentence_has_no_hit(self):
        self.assertEqual(find_hits("a.docx", "paragraph 1", "ご連絡ください。", TERMS), [])

    def test_sentences_are_split_after_the_mark(self):
        self.assertEqual(split_sentences("一文目。二文目！三文目"), ["一文目。", "二文目！", "三文目"])

    def test_known_false_positive_stays_visible(self):
        # "No.10" contains "No.1". It is reported on purpose; a person removes it from the list.
        self.assertEqual(len(find_hits("a.docx", "paragraph 1", "No.10 を参照。", TERMS)), 1)

    def test_known_answer_on_sample_document(self):
        hits = check_folder("samples", load_terms("samples/style_terms.csv"))
        self.assertEqual(sum(1 for h in hits if h.file == "doc_a.docx"), 7)

    def test_table_cell_is_checked(self):
        hits = check_folder("samples", load_terms("samples/style_terms.csv"))
        self.assertTrue(any(h.file == "e2e_doc_c.docx" and h.where.startswith("table") and h.term == "唯一"
                            for h in hits))


if __name__ == "__main__":
    suite = unittest.defaultTestLoader.loadTestsFromTestCase(CheckTermsTest)
    result = unittest.TextTestRunner(stream=sys.stdout, verbosity=2).run(suite)
    sys.exit(0 if result.wasSuccessful() else 1)

schtasks /create /sc weekly /d MON /st 08:00 /tn "TermCheck" /tr "C:\tools\term-check\run.cmd"

"""Run the term check at 9:30 every weekday (Azure Functions, Python v2 model, timer trigger)."""
import logging
import os

import azure.functions as func

app = func.FunctionApp()


# {second} {minute} {hour} {day} {month} {day-of-week}. The default time zone is UTC;
# the Azure Functions docs describe the WEBSITE_TIME_ZONE app setting for other time zones.
@app.timer_trigger(schedule="0 30 9 * * 1-5", arg_name="timer", run_on_startup=False)
def weekday_term_check(timer: func.TimerRequest) -> None:
    if timer.past_due:
        logging.warning("The timer is past due")
    folder = os.environ.get("TERM_CHECK_FOLDER", "")
    logging.info("term check started (folder setting: %s)", folder or "not set")
    # Fetch the changed documents with Microsoft Graph and call check_folder() here
    # (see "Check only documents that changed" in the workflow recipes).