← ClaudeAtlas

codebase-linguistic-analysis-to-csv-exportlisted

Identify all non-English text in a codebase (specifically Portuguese characters) and export findings to a structured CSV for translation/remediation workflows.
Ronnasayd/aipp · ★ 3 · Data & Documents · score 62
Install: claude install-skill Ronnasayd/aipp
# Codebase Linguistic Analysis to CSV Export ## Objective Identify all non-English text in a codebase (specifically Portuguese characters) and export findings to a structured CSV for translation/remediation workflows. --- ## Phase 1: Discovery & Analysis ### Step 1: Define Search Pattern - Identify target language characteristics (e.g., accented characters for Portuguese: `á é í ó ú â ê ô ã õ ç`) - Define regex pattern: `[áéíóúâêôãõç]` captures Portuguese-specific Unicode characters - This pattern catches comments, strings, and identifiers containing Portuguese text ### Step 2: Scope File Types - Restrict search to source code files: `*.ts`, `*.js`, `*.tsx`, `*.jsx` - Exclude `node_modules/` and other dependency directories - Search directory: `/src` (main source) or equivalent project structure ### Step 3: Execute Initial Search - Run: `grep -rn "[áéíóúâêôãõç]" <source_dir> --include="*.ts" --include="*.js"` - Flags: - `-r`: recursive search - `-n`: output line numbers - `--include`: filter by file extension - Output: `file:line:content` format ### Step 4: Quantify Findings - Count total matches: `grep -rn "[áéíóúâêôãõç]" <source_dir> | wc -l` - Result: Total line count with Portuguese text - Group by file: `cut -d: -f1 | sort | uniq -c | sort -rn` - Result: Prioritized file list (highest count first) --- ## Phase 2: Categorization ### Step 5: Classify by Context For each matched line, determine context: - **Comment**: Lines matching `^\s*//` or `^\s*/