2f51ac617f
Some checks failed
CI / go-lint (push) Has been skipped
CI / python-lint (push) Has been skipped
CI / nodejs-lint (push) Has been skipped
CI / test-go-school (push) Successful in 34s
CI / test-go-edu-search (push) Successful in 31s
CI / test-python-klausur (push) Failing after 2m5s
CI / test-python-agent-core (push) Successful in 23s
CI / test-nodejs-website (push) Successful in 22s
fix_cell_phonetics() ersetzt fehlerhafte IPA-Klammern UND fuegt fehlende Lautschrift fuer englische Woerter ein (z.B. badge, film, challenge, profit). Wird auf alle Zellen mit col_type column_en/column_text angewandt. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
118 lines
4.6 KiB
Python
118 lines
4.6 KiB
Python
"""Tests for fix_cell_phonetics and _insert_missing_ipa."""
|
||
|
||
import pytest
|
||
from unittest.mock import patch, MagicMock
|
||
|
||
import sys
|
||
import os
|
||
sys.path.insert(0, os.path.join(os.path.dirname(__file__), '..'))
|
||
|
||
|
||
class TestInsertMissingIpa:
|
||
"""Tests for _insert_missing_ipa function."""
|
||
|
||
def test_single_headword_gets_ipa(self):
|
||
"""Single English headword should get IPA inserted."""
|
||
from cv_ocr_engines import _insert_missing_ipa
|
||
result = _insert_missing_ipa("badge", "british")
|
||
assert "[" in result and "]" in result
|
||
assert result.startswith("badge [")
|
||
|
||
def test_short_phrase_first_word_gets_ipa(self):
|
||
"""First real word in short phrase gets IPA."""
|
||
from cv_ocr_engines import _insert_missing_ipa
|
||
result = _insert_missing_ipa("film", "british")
|
||
assert "[" in result
|
||
|
||
def test_long_sentence_unchanged(self):
|
||
"""Sentences with >6 words should not get IPA."""
|
||
from cv_ocr_engines import _insert_missing_ipa
|
||
text = "Can I borrow your CD player from you please"
|
||
result = _insert_missing_ipa(text, "british")
|
||
assert result == text
|
||
|
||
def test_existing_brackets_unchanged(self):
|
||
"""Text with existing brackets should not get double IPA."""
|
||
from cv_ocr_engines import _insert_missing_ipa
|
||
text = "dance [dˈɑːns]"
|
||
result = _insert_missing_ipa(text, "british")
|
||
assert result == text
|
||
|
||
def test_empty_text_unchanged(self):
|
||
"""Empty text returns empty."""
|
||
from cv_ocr_engines import _insert_missing_ipa
|
||
assert _insert_missing_ipa("", "british") == ""
|
||
assert _insert_missing_ipa(" ", "british") == ""
|
||
|
||
def test_grammar_words_skipped(self):
|
||
"""Grammar particles should not get IPA."""
|
||
from cv_ocr_engines import _insert_missing_ipa
|
||
# "sth" is in _GRAMMAR_BRACKET_WORDS
|
||
result = _insert_missing_ipa("sth", "british")
|
||
assert "[" not in result
|
||
|
||
def test_german_word_no_ipa(self):
|
||
"""German words (no IPA entry) stay unchanged."""
|
||
from cv_ocr_engines import _insert_missing_ipa
|
||
result = _insert_missing_ipa("Anstecknadel", "british")
|
||
assert result == "Anstecknadel"
|
||
|
||
|
||
class TestFixCellPhonetics:
|
||
"""Tests for fix_cell_phonetics function."""
|
||
|
||
def test_english_column_cells_processed(self):
|
||
"""Cells with col_type column_en should be processed."""
|
||
from cv_ocr_engines import fix_cell_phonetics
|
||
cells = [
|
||
{"cell_id": "c1", "col_type": "column_en", "text": "badge"},
|
||
{"cell_id": "c2", "col_type": "column_de", "text": "Anstecknadel"},
|
||
]
|
||
fix_cell_phonetics(cells, pronunciation="british")
|
||
# English cell should have IPA
|
||
assert "[" in cells[0]["text"]
|
||
# German cell should be unchanged
|
||
assert cells[1]["text"] == "Anstecknadel"
|
||
|
||
def test_column_text_cells_processed(self):
|
||
"""Cells with col_type column_text should be processed."""
|
||
from cv_ocr_engines import fix_cell_phonetics
|
||
cells = [
|
||
{"cell_id": "c1", "col_type": "column_text", "text": "challenge"},
|
||
]
|
||
fix_cell_phonetics(cells, pronunciation="british")
|
||
assert "[" in cells[0]["text"]
|
||
|
||
def test_garbled_ipa_replaced(self):
|
||
"""Garbled IPA brackets should be replaced with correct IPA."""
|
||
from cv_ocr_engines import fix_cell_phonetics
|
||
cells = [
|
||
{"cell_id": "c1", "col_type": "column_en", "text": "dance {'tfatno]"},
|
||
]
|
||
fix_cell_phonetics(cells, pronunciation="british")
|
||
# Should have proper IPA now
|
||
text = cells[0]["text"]
|
||
assert "dance [" in text
|
||
assert "{'tfatno]" not in text
|
||
|
||
def test_empty_cells_unchanged(self):
|
||
"""Empty cells should not cause errors."""
|
||
from cv_ocr_engines import fix_cell_phonetics
|
||
cells = [
|
||
{"cell_id": "c1", "col_type": "column_en", "text": ""},
|
||
{"cell_id": "c2", "col_type": "column_en", "text": None},
|
||
]
|
||
fix_cell_phonetics(cells, pronunciation="british")
|
||
assert cells[0]["text"] == ""
|
||
|
||
def test_non_english_col_types_skipped(self):
|
||
"""Cells with column_de, column_example etc. should not be processed."""
|
||
from cv_ocr_engines import fix_cell_phonetics
|
||
cells = [
|
||
{"cell_id": "c1", "col_type": "column_de", "text": "Eis (gefrorenes Wasser)"},
|
||
{"cell_id": "c2", "col_type": "column_example", "text": "(sich beschweren)"},
|
||
]
|
||
fix_cell_phonetics(cells, pronunciation="british")
|
||
assert cells[0]["text"] == "Eis (gefrorenes Wasser)"
|
||
assert cells[1]["text"] == "(sich beschweren)"
|