Chaim
3f759d3610
- Add delete_document_chunks for reprocessing, save extracted text to disk - Expand case directory structure (original/extracted/proofread/backup) - Update classifier patterns (תגובה, הודעת עמדה) - Fix proofreader agent paths for new directory layout - Update HEARTBEAT to notify on every task completion - Improve bidi_table with LRE/PDF directional embedding - Add Paperclip project verification and auto-close setup issue - Add auto-sync-cases.sh for Gitea synchronization Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
76 lines
2.7 KiB
Python
76 lines
2.7 KiB
Python
#!/usr/bin/env python3
|
|
"""BiDi-safe box-drawing table renderer for mixed Hebrew/English terminal output.
|
|
|
|
Uses Unicode directional marks to prevent the BiDi algorithm from breaking
|
|
table alignment when Hebrew text is present.
|
|
|
|
Usage as module:
|
|
from scripts.bidi_table import bidi_table
|
|
print(bidi_table(['Col1', 'Col2'], [['val1', 'ערך2']]))
|
|
|
|
Usage from CLI:
|
|
python3 scripts/bidi_table.py
|
|
"""
|
|
|
|
from __future__ import annotations
|
|
|
|
import re
|
|
|
|
LRM = "\u200E" # Left-to-Right Mark
|
|
RLM = "\u200F" # Right-to-Left Mark
|
|
LRE = "\u202A" # Left-to-Right Embedding
|
|
PDF = "\u202C" # Pop Directional Formatting
|
|
|
|
_HEB_RE = re.compile(r'[\u0590-\u05FF]')
|
|
|
|
|
|
def _has_hebrew(text: str) -> bool:
|
|
return bool(_HEB_RE.search(text))
|
|
|
|
|
|
def bidi_table(headers: list[str], rows: list[list[str]]) -> str:
|
|
"""Render a box-drawing table safe for mixed RTL/LTR terminal display."""
|
|
ncols = len(headers)
|
|
|
|
# Calculate column widths (visual length, not counting bidi marks)
|
|
col_widths = [len(h) for h in headers]
|
|
for row in rows:
|
|
for i, cell in enumerate(row[:ncols]):
|
|
col_widths[i] = max(col_widths[i], len(cell))
|
|
|
|
def hline(left: str, mid: str, right: str) -> str:
|
|
return left + mid.join("─" * (w + 2) for w in col_widths) + right
|
|
|
|
def dataline(cells: list[str]) -> str:
|
|
parts = []
|
|
for i in range(ncols):
|
|
cell = cells[i] if i < len(cells) else ""
|
|
padded = cell + " " * max(0, col_widths[i] - len(cell))
|
|
# Wrap each cell: LRE forces left-to-right context for the cell,
|
|
# so box-drawing chars stay in place. PDF closes the embedding.
|
|
parts.append(LRE + " " + padded + " " + PDF)
|
|
return LRM + "│" + ("│").join(parts) + "│"
|
|
|
|
lines = [hline("┌", "┬", "┐")]
|
|
lines.append(dataline(headers))
|
|
lines.append(hline("├", "┼", "┤"))
|
|
for row in rows:
|
|
lines.append(dataline(row))
|
|
lines.append(hline("└", "┴", "┘"))
|
|
return "\n".join(lines)
|
|
|
|
|
|
if __name__ == "__main__":
|
|
table = bidi_table(
|
|
["File", "Description", "Model", "Step"],
|
|
[
|
|
["claims_extractor.py", "חילוץ טענות מכתבי טענות", "Sonnet", "שלב 3 — הבא בתור"],
|
|
["brainstorm.py", "סיעור מוחות — כיווני נימוק", "Sonnet", "שלב 4"],
|
|
["block_writer.py", "כתיבת בלוקים של החלטה", "Sonnet/Opus", "שלב 5"],
|
|
["qa_validator.py", "בדיקת איכות QA", "Sonnet", "שלב 6"],
|
|
["style_analyzer.py", "ניתוח סגנון דפנה", "Opus", "חד-פעמי"],
|
|
["learning_loop.py", "למידה מהחלטה סופית", "Sonnet", "סוף תהליך"],
|
|
],
|
|
)
|
|
print(table)
|