3374bd8b20
- Add extractors for Italian sources: it_m3.xls and italian.json - Add comparison script (compare-italian.py) to report source overlaps and conflicts - Add merge script (merge-italian-json.py) with priority order ['italian', 'it_m3'] - Output authoritative dataset to datafiles/italian-merged.json - Update README to document both English and Italian pipelines
91 lines
2.7 KiB
Python
91 lines
2.7 KiB
Python
#!/usr/bin/env python3
|
|
"""
|
|
scripts/extraction-scripts/italian/extract-italian-json.py
|
|
|
|
Extracts CEFR data from italian.json (Italian flashcard source).
|
|
Filters for useful_for_flashcard=true and supported POS (noun, verb).
|
|
"""
|
|
|
|
import json
|
|
from pathlib import Path
|
|
|
|
# Constants matching @glossa/shared
|
|
SUPPORTED_POS = ["noun", "verb"]
|
|
CEFR_LEVELS = ["A1", "A2", "B1", "B2", "C1", "C2"]
|
|
|
|
# Paths (relative to project root)
|
|
INPUT_FILE = Path("scripts/data-sources/italian/italian.json")
|
|
OUTPUT_FILE = Path("scripts/data-sources/italian/italian-extracted.json")
|
|
|
|
|
|
def extract() -> None:
|
|
print(f"Reading: {INPUT_FILE}")
|
|
|
|
with open(INPUT_FILE, "r", encoding="utf-8") as f:
|
|
data = json.load(f)
|
|
|
|
records = []
|
|
skipped_pos = 0
|
|
skipped_not_useful = 0
|
|
skipped_invalid_cefr = 0
|
|
skipped_empty_word = 0
|
|
|
|
for entry in data:
|
|
# Filter: must be useful for flashcard
|
|
if not entry.get("useful_for_flashcard", False):
|
|
skipped_not_useful += 1
|
|
continue
|
|
|
|
# Filter: must have supported POS
|
|
pos = entry.get("pos", "").lower().strip()
|
|
if pos not in SUPPORTED_POS:
|
|
skipped_pos += 1
|
|
continue
|
|
|
|
# Filter: must have valid CEFR level
|
|
cefr = entry.get("cefr_level", "").upper().strip()
|
|
if cefr not in CEFR_LEVELS:
|
|
skipped_invalid_cefr += 1
|
|
continue
|
|
|
|
# Normalize word
|
|
word = entry.get("word", "").lower().strip()
|
|
if not word:
|
|
skipped_empty_word += 1
|
|
continue
|
|
|
|
record = {"word": word, "pos": pos, "cefr": cefr, "source": "italian"}
|
|
records.append(record)
|
|
|
|
# Write output
|
|
with open(OUTPUT_FILE, "w", encoding="utf-8") as f:
|
|
json.dump(records, f, indent=2, ensure_ascii=False)
|
|
|
|
# Stats
|
|
noun_count = sum(1 for r in records if r["pos"] == "noun")
|
|
verb_count = sum(1 for r in records if r["pos"] == "verb")
|
|
|
|
cefr_distribution = {}
|
|
for level in CEFR_LEVELS:
|
|
count = sum(1 for r in records if r["cefr"] == level)
|
|
if count > 0:
|
|
cefr_distribution[level] = count
|
|
|
|
print(f"\nExtracted: {len(records)} records")
|
|
print(f" - Nouns: {noun_count}")
|
|
print(f" - Verbs: {verb_count}")
|
|
print("\nCEFR distribution:")
|
|
for level in CEFR_LEVELS:
|
|
if level in cefr_distribution:
|
|
print(f" - {level}: {cefr_distribution[level]}")
|
|
|
|
print("\nSkipped:")
|
|
print(f" - Not useful for flashcard: {skipped_not_useful}")
|
|
print(f" - Unsupported POS: {skipped_pos}")
|
|
print(f" - Invalid CEFR: {skipped_invalid_cefr}")
|
|
print(f" - Empty word: {skipped_empty_word}")
|
|
print(f"\nOutput: {OUTPUT_FILE}")
|
|
|
|
|
|
if __name__ == "__main__":
|
|
extract()
|