docs(ecp): add Club Atlético River Plate ECP profile and update classification examples

This commit is contained in:
2026-08-21 10:43:48 -03:00
parent 926a6b8cfc
commit cb33dafac1
16 changed files with 2411 additions and 1535 deletions
+10 -6
View File
@@ -98,7 +98,7 @@
"96": "readiness.md",
"97": "🧠 TextNLPClassifierApp",
"98": "Extraction Pipeline Checklist: Article Content Multi-Engine Extractor",
"99": "sample_rss_xml",
"99": "parametrize",
"100": "models.py",
"101": "ECPSnapshot",
"102": "Feature Specification: Multilingual NLP Entity Inherence Classifier (POC)",
@@ -116,7 +116,7 @@
"114": "JSON Schema Contract: Article Content Multi-Engine Extractor",
"115": "PRD — Seleção determinística da biblioteca de extração de conteúdo",
"116": "select_article_extractor.py",
"117": "Research & Architectural Decisions: Deterministic Content Selection",
"117": "1. Text Normalization Pipeline",
"118": "Tasks: Deterministic Article Content Selection",
"119": "select_article_extractor",
"120": "process_batch",
@@ -148,16 +148,20 @@
"146": "Specification Quality Checklist: Convert Article JSON to Markdown",
"147": "CLI Contract: `convert_article_to_markdown.py`",
"148": "9. Interface CLI",
"149": "1. Text Normalization Pipeline",
"149": "get_hl_gl_ceid",
"150": "13. Estratégia de testes",
"151": "6. Contrato de entrada",
"152": "assemble_markdown_document",
"153": "convert_html_to_markdown",
"154": "remove_duplicate_initial_h1",
"154": "JSON Schema Contract: Deterministic Article Content Selection",
"155": "5. Escopo",
"156": "Los puntajes de River vs. Independiente Santa Fe, por la Copa Sudamericana - TyC Sports",
"157": "valid_newspaper4k.md",
"158": "valid_readability.md",
"159": "test_normalize_list_strings_and_deduplication",
"160": "test_validate_url_schemes"
"159": "test_normalize_date_rfc_2822_variants",
"160": "test_normalize_date_invalid_and_placeholders",
"161": "test_metadata_priority_title_all_fallbacks",
"162": "test_metadata_priority_subtitle_omitted_when_equal_to_title",
"163": "test_metadata_priority_first_valid_source_no_cross_merging",
"164": "test_normalize_scalar_non_string_types"
}