feat: block Korean prose contract violations

src/claridoc/style_contracts.py

@@ -39,6 +39,7 @@ Write Korean reader-facing prose as a supported first-person experience, not as
 """
 
 _PLAIN_FORM_ENDING = re.compile(r"(?<!니)다(?=[.!?](?:\s|$))")
+_FIRST_PERSON = re.compile(r"(?:저는|제가)")
 _FENCE = re.compile(r"^\s*(?:```|~~~)")
 _HEADING = re.compile(r"^\s{0,3}(#{1,6})\s+(.+?)\s*$")
 _IMAGE_ONLY = re.compile(r"^\s*!\[[^\]]*\]\([^)]*\)\s*$")
@@ -159,3 +160,37 @@ def plain_form_ending_locations(markdown: str) -> list[int]:
     for segment in reader_prose_segments(markdown):
         locations.extend(segment.line for _ in _PLAIN_FORM_ENDING.finditer(segment.text))
     return locations
+
+
+def first_person_metrics(markdown: str) -> dict[str, int | float | bool]:
+    segments = reader_prose_segments(markdown)
+    first_person_marker_count = sum(
+        len(_FIRST_PERSON.findall(segment.text))
+        for segment in segments
+    )
+    opening_has_first_person = bool(
+        segments and _FIRST_PERSON.search(segments[0].text)
+    )
+
+    section_markers: dict[str, bool] = {}
+    for segment in segments:
+        if segment.h2_title is None:
+            continue
+        section_markers.setdefault(segment.h2_title, False)
+        if _FIRST_PERSON.search(segment.text):
+            section_markers[segment.h2_title] = True
+
+    experience_section_count = len(section_markers)
+    marked_experience_section_count = sum(section_markers.values())
+    experience_section_coverage = (
+        marked_experience_section_count / experience_section_count
+        if experience_section_count
+        else 0.0
+    )
+    return {
+        "first_person_marker_count": first_person_marker_count,
+        "opening_has_first_person": opening_has_first_person,
+        "experience_section_count": experience_section_count,
+        "marked_experience_section_count": marked_experience_section_count,
+        "experience_section_coverage": round(experience_section_coverage, 3),
+    }