extraction, comparison and merging scripts for english are done, final english.json exists

scripts/extraction-scripts/english/extract-en_m3.py

@@ -0,0 +1,107 @@
+#!/usr/bin/env python3
+"""
+scripts/extraction-scripts/english/extract-en_m3.py
+
+Extracts CEFR data from en_m3.xls (M3 wordlist).
+"""
+
+import json
+from pathlib import Path
+
+import xlrd
+
+# Constants matching @glossa/shared
+SUPPORTED_POS = ["noun", "verb"]
+CEFR_LEVELS = ["A1", "A2", "B1", "B2", "C1", "C2"]
+
+# POS mapping (case-insensitive)
+POS_MAP = {
+    "noun": "noun",
+    "verb": "verb",
+}
+
+# Paths (relative to project root)
+INPUT_FILE = Path("scripts/data-sources/english/en_m3.xls")
+OUTPUT_FILE = Path("scripts/data-sources/english/en_m3-extracted.json")
+
+
+def extract() -> None:
+    print(f"Reading: {INPUT_FILE}")
+
+    records = []
+    skipped_pos = 0
+    skipped_invalid_cefr = 0
+    skipped_empty_word = 0
+    total_rows = 0
+
+    wb = xlrd.open_workbook(INPUT_FILE)
+    ws = wb.sheet_by_index(0)
+
+    # Skip header row, start from row 1
+    for row_idx in range(1, ws.nrows):
+        total_rows += 1
+
+        # Unpack columns: ID number, Word, Part of Speech, CEFR, Points
+        word_raw = ws.cell_value(row_idx, 1)
+        pos_raw = ws.cell_value(row_idx, 2)
+        cefr_raw = ws.cell_value(row_idx, 3)
+
+        # Normalize POS (case-insensitive)
+        pos = str(pos_raw).lower().strip() if pos_raw else ""
+        if pos not in POS_MAP:
+            skipped_pos += 1
+            continue
+
+        pos = POS_MAP[pos]
+
+        # Normalize CEFR - handle smart quotes
+        cefr_str = str(cefr_raw).strip() if cefr_raw else ""
+        # Strip Unicode smart quotes (U+201C and U+201D)
+        cefr_str = cefr_str.strip("\u201c\u201d")
+        cefr = cefr_str.upper()
+
+        if cefr not in CEFR_LEVELS:
+            skipped_invalid_cefr += 1
+            continue
+
+        # Normalize word
+        word = str(word_raw).lower().strip() if word_raw else ""
+        if not word:
+            skipped_empty_word += 1
+            continue
+
+        record = {"word": word, "pos": pos, "cefr": cefr, "source": "en_m3"}
+        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"\nTotal rows in XLS: {total_rows}")
+    print(f"Extracted: {len(records)} records")
+    print(f"  - Nouns: {noun_count}")
+    print(f"  - Verbs: {verb_count}")
+    print(f"\nCEFR distribution:")
+    for level in CEFR_LEVELS:
+        if level in cefr_distribution:
+            print(f"  - {level}: {cefr_distribution[level]}")
+
+    print(f"\nSkipped:")
+    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()