sepehr
07c4c12e6a
All checks were successful
Deploy to Production / Build and Deploy (push) Successful in 2m19s
Multiple translation bugs in Word/Excel/PPTX that caused chart elements
to be left untranslated or charts to render as empty series.
Backend
-------
* providers (deepseek/openai/minimax): tighten system prompt so the LLM
actually translates chart titles/axis labels/legend/category labels,
month abbreviations, and clarifies what counts as a 'real' proper noun
(people/place/company/product names) vs. technical labels. Old rule
'keep proper nouns unchanged' was being read too broadly by the model
and caused chart text to be skipped.
* excel_translator.py:
- Sheet reference rewrite: when a sheet is renamed, the chart XML's
c:f refs (e.g. 'Sales 2024'!$D$2:$D$61) are now rewritten to the
new name with proper apostrophe escaping (Chiffre d'affaires ->
'Chiffre d''affaires') and auto-quoting when the new name contains
spaces or special chars. Without this, the chart points at a sheet
that no longer exists and renders 0/empty series.
- Sheet name offset bug: sheet_name_offset was computed after chart
text was appended to text_elements, causing sheet names to receive
chart text translations. Now captured BEFORE sheet names are added.
* New tests:
- test_excel_chart_sheet_refs.py (10 unit tests, synthetic inputs)
- test_chart_translation_prompt.py (3 contract tests on the prompt)
Frontend
--------
* DashboardSidebar / translate/page: hide the Memento promo section
for paying users (tier != 'free').
* constants.ts: temporarily comment out the 'CLES API' nav item.
Update constants.test.ts to match the new state.
All fixes are generic - no file-specific hardcoding, edge cases covered
(empty mapping, missing bang, apostrophe escaping, partial renames,
multi-series).
51 lines
1.7 KiB
Python
51 lines
1.7 KiB
Python
"""Verify all 3 provider prompts are identical and contain chart-translation rules.
|
|
|
|
This is a regression test for the bug where chart titles/legends/category labels
|
|
were left untranslated because the system prompt was too ambiguous about
|
|
"proper nouns or brand names".
|
|
"""
|
|
import sys
|
|
from pathlib import Path
|
|
|
|
sys.path.insert(0, str(Path(__file__).resolve().parents[1]))
|
|
|
|
from services.providers.deepseek_provider import DEFAULT_TRANSLATION_PROMPT as P1
|
|
from services.providers.minimax_provider import DEFAULT_TRANSLATION_PROMPT as P3
|
|
from services.providers.openai_provider import DEFAULT_TRANSLATION_PROMPT as P2
|
|
|
|
REQUIRED_PHRASES = [
|
|
"Chart elements",
|
|
"MUST always be translated",
|
|
"Translate month and weekday abbreviations",
|
|
"Jan",
|
|
"janvier",
|
|
"Keep ONLY real proper nouns",
|
|
"Google, Microsoft",
|
|
"API, URL, HTTP, JSON",
|
|
]
|
|
|
|
|
|
def test_all_prompts_identical():
|
|
assert P1 == P2 == P3, "All 3 provider prompts must be identical"
|
|
|
|
|
|
def test_prompt_contains_required_rules():
|
|
for phrase in REQUIRED_PHRASES:
|
|
assert phrase in P1, f"Missing rule: {phrase!r}"
|
|
|
|
|
|
def test_prompt_drops_old_ambiguous_rule():
|
|
# The old "If the text contains proper nouns or brand names" rule was
|
|
# the root cause of chart labels not being translated. The new prompt
|
|
# uses a more specific rule that lists what counts as a proper noun.
|
|
assert "If the text contains proper nouns or brand names" not in P1, (
|
|
"Old ambiguous rule still present — chart labels will be skipped again"
|
|
)
|
|
|
|
|
|
if __name__ == "__main__":
|
|
test_all_prompts_identical()
|
|
test_prompt_contains_required_rules()
|
|
test_prompt_drops_old_ambiguous_rule()
|
|
print("All prompt regression tests passed.")
|