chore: 문서 수정

src/claridoc/style_contracts.py

@@ -1,5 +1,8 @@
 from __future__ import annotations
 
+import re
+from dataclasses import dataclass
+
 from claridoc.models import Brief, DocumentType
 
 
@@ -35,6 +38,29 @@ Write Korean reader-facing prose as a supported first-person experience, not as
 - Use conversational but disciplined Korean. A Korean developer should be able to say the sentence naturally to a colleague without turning it into forced colloquial speech.
 """
 
+_PLAIN_FORM_ENDING = re.compile(r"(?<!니)다(?=[.!?](?:\s|$))")
+_FENCE = re.compile(r"^\s*(?:```|~~~)")
+_HEADING = re.compile(r"^\s{0,3}(#{1,6})\s+(.+?)\s*$")
+_IMAGE_ONLY = re.compile(r"^\s*!\[[^\]]*\]\([^)]*\)\s*$")
+_TABLE_DIVIDER = re.compile(
+    r"^\s*\|?\s*:?-{3,}:?\s*(?:\|\s*:?-{3,}:?\s*)+\|?\s*$"
+)
+_QUOTED_SPANS = (
+    re.compile(r'"[^"\n]*"'),
+    re.compile(r"'[^'\n]*'"),
+    re.compile(r"“[^”\n]*”"),
+    re.compile(r"‘[^’\n]*’"),
+    re.compile(r"「[^」\n]*」"),
+    re.compile(r"『[^』\n]*』"),
+)
+
+
+@dataclass(frozen=True, slots=True)
+class ReaderProseSegment:
+    text: str
+    line: int
+    h2_title: str | None
+
 
 def korean_experience_contract_applies(brief: Brief) -> bool:
     if not brief.is_korean:
@@ -72,3 +98,64 @@ def revision_style_protocol(brief: Brief) -> str:
 After resolving individual findings, recheck 문서 전체(the complete document) against `korean_first_person_experience_v1`.
 Do not stop after adding one `저는` sentence. Confirm the opening and major transitions still form supported experience threads, all reader prose still uses `합니다/했습니다`, unfamiliar terms remain explained at first need, and no compliant section regressed during the whole-document rewrite.
 """
+
+
+def reader_prose_segments(markdown: str) -> list[ReaderProseSegment]:
+    segments: list[ReaderProseSegment] = []
+    in_fence = False
+    current_h2: str | None = None
+    lines = markdown.splitlines()
+    table_lines: set[int] = set()
+    for index, line in enumerate(lines):
+        if not _TABLE_DIVIDER.match(line):
+            continue
+        if index > 0 and "|" in lines[index - 1]:
+            table_lines.add(index - 1)
+        table_lines.add(index)
+        cursor = index + 1
+        while cursor < len(lines) and lines[cursor].strip() and "|" in lines[cursor]:
+            table_lines.add(cursor)
+            cursor += 1
+
+    for line_number, raw_line in enumerate(lines, start=1):
+        if _FENCE.match(raw_line):
+            in_fence = not in_fence
+            continue
+        if in_fence:
+            continue
+
+        heading = _HEADING.match(raw_line)
+        if heading:
+            if len(heading.group(1)) == 2:
+                current_h2 = heading.group(2).strip()
+            continue
+
+        stripped = raw_line.strip()
+        if (
+            not stripped
+            or line_number - 1 in table_lines
+            or stripped.startswith(">")
+            or raw_line.startswith(("    ", "\t"))
+            or _IMAGE_ONLY.match(raw_line)
+            or _TABLE_DIVIDER.match(raw_line)
+            or (stripped.startswith("|") and stripped.endswith("|"))
+        ):
+            continue
+
+        prose = re.sub(r"!\[[^\]]*\]\([^)]*\)", "", stripped)
+        prose = re.sub(r"\[([^\]]+)\]\([^)]*\)", r"\1", prose)
+        prose = re.sub(r"`[^`\n]*`", "", prose)
+        for quoted_span in _QUOTED_SPANS:
+            prose = quoted_span.sub("", prose)
+        prose = re.sub(r"^\s*(?:[-*+]|\d+[.)])\s+", "", prose).strip()
+        if prose:
+            segments.append(ReaderProseSegment(prose, line_number, current_h2))
+
+    return segments
+
+
+def plain_form_ending_locations(markdown: str) -> list[int]:
+    locations: list[int] = []
+    for segment in reader_prose_segments(markdown):
+        locations.extend(segment.line for _ in _PLAIN_FORM_ENDING.finditer(segment.text))
+    return locations