esg-cid-plus 0.1.0__tar.gz

esg_cid_plus-0.1.0/.gitignore

@@ -0,0 +1,244 @@
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[codz]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py.cover
+.hypothesis/
+.pytest_cache/
+cover/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+.pybuilder/
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+#   For a library or package, you might want to ignore these files since the code is
+#   intended to run in multiple environments; otherwise, check them in:
+# .python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# UV
+#   Similar to Pipfile.lock, it is generally recommended to include uv.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+uv.lock
+
+# poetry
+#   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
+#poetry.lock
+#poetry.toml
+
+# pdm
+#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#   pdm recommends including project-wide configuration in pdm.toml, but excluding .pdm-python.
+#   https://pdm-project.org/en/latest/usage/project/#working-with-version-control
+#pdm.lock
+#pdm.toml
+.pdm-python
+.pdm-build/
+
+# pixi
+#   Similar to Pipfile.lock, it is generally recommended to include pixi.lock in version control.
+#pixi.lock
+#   Pixi creates a virtual environment in the .pixi directory, just like venv module creates one
+#   in the .venv directory. It is recommended not to include this directory in version control.
+.pixi
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.envrc
+!.env.example
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# pytype static type analyzer
+.pytype/
+
+# Cython debug symbols
+cython_debug/
+
+# PyCharm
+#  JetBrains specific template is maintained in a separate JetBrains.gitignore that can
+#  be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
+#  and can be added to the global gitignore or merged into this file.  For a more nuclear
+#  option (not recommended) you can uncomment the following to ignore the entire idea folder.
+#.idea/
+
+# Abstra
+# Abstra is an AI-powered process automation framework.
+# Ignore directories containing user credentials, local state, and settings.
+# Learn more at https://abstra.io/docs
+.abstra/
+
+# Visual Studio Code
+#  Visual Studio Code specific template is maintained in a separate VisualStudioCode.gitignore 
+#  that can be found at https://github.com/github/gitignore/blob/main/Global/VisualStudioCode.gitignore
+#  and can be added to the global gitignore or merged into this file. However, if you prefer, 
+#  you could uncomment the following to ignore the entire vscode folder
+# .vscode/
+
+# Ruff stuff:
+.ruff_cache/
+
+# PyPI configuration file
+.pypirc
+
+# Cursor
+#  Cursor is an AI-powered code editor. `.cursorignore` specifies files/directories to
+#  exclude from AI features like autocomplete and code analysis. Recommended for sensitive data
+#  refer to https://docs.cursor.com/context/ignore-files
+.cursorignore
+.cursorindexingignore
+
+# Marimo
+marimo/_static/
+marimo/_lsp/
+__marimo__/
+
+# ACM Paper
+acm_paper/
+
+.vscode/
+.claude/
+.codex/
+
+.awd/
+
+data/
+!libs/**/data/
+
+archive/
+
+output/
+outputs/
+optimized/
+
+**.aux
+**.out
+**.bbl
+**.blg
+**.fdb_latexmk
+**.fls
+neurips_paper/
+
+# mlflow
+mlflow*.db
+mlartifacts*/
+mlruns/
+
+.superpowers/
+
+# private skills (must not leak into eval / released dataset)
+.agents/skills/annotate-gri-hard/

esg_cid_plus-0.1.0/PKG-INFO

@@ -0,0 +1,79 @@
+Metadata-Version: 2.4
+Name: esg-cid-plus
+Version: 0.1.0
+Summary: ESG-CID-Plus: A Stratified Benchmark for Disclosure Content Index Table Extraction from Corporate Sustainability Reports
+Project-URL: Homepage, https://github.com/anomalyco/esg-cid-plus
+Author-email: Rehan Ahmed <shafiuddin.r.ahmed@accenture.com>
+License: MIT
+Keywords: benchmark,content-index,esg,pdf-extraction,sustainability
+Classifier: Development Status :: 4 - Beta
+Classifier: Intended Audience :: Developers
+Classifier: Intended Audience :: Science/Research
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.13
+Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
+Requires-Python: >=3.13
+Requires-Dist: camelot-py>=0.11.0
+Requires-Dist: datasets>=2.0
+Requires-Dist: img2table>=2.0
+Requires-Dist: lunr>=0.7.0
+Requires-Dist: opencv-python-headless>=4.8
+Requires-Dist: pdfminer-six>=20231228
+Requires-Dist: pdfplumber>=0.11.9
+Requires-Dist: pillow>=10.0.0
+Requires-Dist: pydantic>=2.0
+Requires-Dist: pypdfium2>=4.0.0
+Requires-Dist: python-dotenv>=1.0
+Requires-Dist: rapidocr-onnxruntime>=1.4
+Description-Content-Type: text/markdown
+
+# esg-cid-plus
+
+Supporting code for the EMNLP 2026 paper:
+**ESG-CID-Plus: A Stratified Benchmark for Disclosure Content Index Table Extraction from Corporate Sustainability Reports**
+
+## Install
+
+```bash
+uv pip install -e .
+```
+
+## Modules
+
+| Module | Purpose |
+|--------|---------|
+| `cid` | Data models (`CIRow`, `ContentIndex`, `FrameworkSpec`) and normalization helpers |
+| `data` | HuggingFace loaders — `load_split`, `load_framework`, `resolve_pdf_path` |
+| `pdf_toolkit` | `PDFSession` — text extraction, lunr search, camelot tables, page labels |
+| `pdf_toolkit_ocr` | `OCRPDFSession` — extends above with image rendering, rapidocr, img2table |
+| `extract` | Rule-based pipeline: S1 detect → S2/S3 draft → S4 resolve → `ContentIndex` |
+| `eval` | Tuple-level P/R/F1 — `evaluate_predictions`, `format_feedback` |
+
+## Quickstart
+
+```python
+from esg_cid_plus.data import load_split, load_framework, resolve_pdf_path
+from esg_cid_plus.extract import extract
+from esg_cid_plus.eval import evaluate_predictions
+
+pdf_rows, cid_rows = load_split("train_small")
+fw = load_framework("gri_2021")
+
+pdf_path = resolve_pdf_path(pdf_rows[0])
+ci = extract(pdf_path, fw)
+
+gt = [r for r in cid_rows if r["report_name"] == pdf_rows[0]["report_name"]]
+pred = [{"report_name": ci.report_name, "standard_id": r.standard_id,
+         "page_location_indices": r.page_location_indices} for r in ci.rows]
+
+_, overall = evaluate_predictions(gt, pred)
+print(overall)
+```
+
+## Tests
+
+```bash
+uv run pytest              # fast (unit)
+uv run pytest -m slow      # integration — requires HuggingFace access
+```

esg_cid_plus-0.1.0/README.md

@@ -0,0 +1,49 @@
+# esg-cid-plus
+
+Supporting code for the EMNLP 2026 paper:
+**ESG-CID-Plus: A Stratified Benchmark for Disclosure Content Index Table Extraction from Corporate Sustainability Reports**
+
+## Install
+
+```bash
+uv pip install -e .
+```
+
+## Modules
+
+| Module | Purpose |
+|--------|---------|
+| `cid` | Data models (`CIRow`, `ContentIndex`, `FrameworkSpec`) and normalization helpers |
+| `data` | HuggingFace loaders — `load_split`, `load_framework`, `resolve_pdf_path` |
+| `pdf_toolkit` | `PDFSession` — text extraction, lunr search, camelot tables, page labels |
+| `pdf_toolkit_ocr` | `OCRPDFSession` — extends above with image rendering, rapidocr, img2table |
+| `extract` | Rule-based pipeline: S1 detect → S2/S3 draft → S4 resolve → `ContentIndex` |
+| `eval` | Tuple-level P/R/F1 — `evaluate_predictions`, `format_feedback` |
+
+## Quickstart
+
+```python
+from esg_cid_plus.data import load_split, load_framework, resolve_pdf_path
+from esg_cid_plus.extract import extract
+from esg_cid_plus.eval import evaluate_predictions
+
+pdf_rows, cid_rows = load_split("train_small")
+fw = load_framework("gri_2021")
+
+pdf_path = resolve_pdf_path(pdf_rows[0])
+ci = extract(pdf_path, fw)
+
+gt = [r for r in cid_rows if r["report_name"] == pdf_rows[0]["report_name"]]
+pred = [{"report_name": ci.report_name, "standard_id": r.standard_id,
+         "page_location_indices": r.page_location_indices} for r in ci.rows]
+
+_, overall = evaluate_predictions(gt, pred)
+print(overall)
+```
+
+## Tests
+
+```bash
+uv run pytest              # fast (unit)
+uv run pytest -m slow      # integration — requires HuggingFace access
+```

esg_cid_plus-0.1.0/pyproject.toml

@@ -0,0 +1,60 @@
+[project]
+name = "esg-cid-plus"
+version = "0.1.0"
+description = "ESG-CID-Plus: A Stratified Benchmark for Disclosure Content Index Table Extraction from Corporate Sustainability Reports"
+readme = "README.md"
+license = { text = "MIT" }
+authors = [{ name = "Rehan Ahmed", email = "shafiuddin.r.ahmed@accenture.com" }]
+keywords = ["esg", "content-index", "pdf-extraction", "benchmark", "sustainability"]
+classifiers = [
+    "Development Status :: 4 - Beta",
+    "Intended Audience :: Science/Research",
+    "Intended Audience :: Developers",
+    "License :: OSI Approved :: MIT License",
+    "Programming Language :: Python :: 3",
+    "Programming Language :: Python :: 3.13",
+    "Topic :: Scientific/Engineering :: Artificial Intelligence",
+]
+requires-python = ">=3.13"
+dependencies = [
+    "pdfplumber>=0.11.9",
+    "pdfminer.six>=20231228",
+    "camelot-py>=0.11.0",
+    "opencv-python-headless>=4.8",
+    "lunr>=0.7.0",
+    "pydantic>=2.0",
+    "datasets>=2.0",
+    "python-dotenv>=1.0",
+    "pypdfium2>=4.0.0",
+    "rapidocr-onnxruntime>=1.4",
+    "img2table>=2.0",
+    "Pillow>=10.0.0",
+]
+
+[project.urls]
+Homepage = "https://github.com/anomalyco/esg-cid-plus"
+
+[dependency-groups]
+dev = ["pytest", "ruff"]
+
+[build-system]
+requires = ["hatchling"]
+build-backend = "hatchling.build"
+
+[tool.hatch.build.targets.wheel]
+packages = ["src/esg_cid_plus"]
+
+[tool.ruff]
+line-length = 100
+target-version = "py313"
+extend-exclude = [".awd"]
+
+[tool.ruff.lint]
+select = ["E", "F", "I", "W", "UP"]
+ignore = ["E501"]
+
+[tool.pytest.ini_options]
+testpaths = ["tests"]
+markers = [
+    "slow: integration tests that download real PDFs from HuggingFace (deselect with -m 'not slow')",
+]

esg_cid_plus-0.1.0/src/esg_cid_plus/cid.py

@@ -0,0 +1,189 @@
+"""CID data models and normalization helpers.
+
+Defines the core types for Content Index Detection:
+  - CIRow / ContentIndex  — pydantic models for one row / one full index
+  - FrameworkSpec / DisclosureDef — framework schema loaded from HuggingFace
+  - normalize_standard_id / parse_page_indices / row_page_set
+"""
+
+from __future__ import annotations
+
+import json
+import re
+from dataclasses import dataclass, field
+from pathlib import Path
+
+from pydantic import BaseModel, Field, field_validator
+
+# ── Normalization helpers ─────────────────────────────────────────────────────
+
+_STANDARD_ID_DASH_RE = re.compile(r"\s*[-–—]\s*")
+_PAGE_RANGE_TO_RE = re.compile(r"(\d+)\s+to\s+(\d+)")
+_PAGE_SENTINELS = {"n/a", "na", "-", "notapplicable", "not applicable", ""}
+
+
+def normalize_standard_id(sid: str) -> str:
+    """Strip framework prefixes and normalize dashes.
+
+    >>> normalize_standard_id("GRI 2-1")
+    '2-1'
+    >>> normalize_standard_id("102 - 1")
+    '102-1'
+    """
+    sid = sid.strip()
+    for prefix in ("GRI ", "ESRS ", "SASB "):
+        if sid.startswith(prefix):
+            sid = sid[len(prefix):]
+            break
+    return _STANDARD_ID_DASH_RE.sub("-", sid.strip())
+
+
+def parse_page_indices(v: str | list[int]) -> list[int]:
+    """Parse 0-based page indices from a string or list, expanding ranges.
+
+    >>> parse_page_indices("133-137")
+    [133, 134, 135, 136, 137]
+    >>> parse_page_indices("2, 4, 16-23")
+    [2, 4, 16, 17, 18, 19, 20, 21, 22, 23]
+    """
+    if isinstance(v, list):
+        return list(v)
+    v = _PAGE_RANGE_TO_RE.sub(r"\1-\2", v.strip())
+    result: list[int] = []
+    for part in v.split(","):
+        part = part.strip()
+        if not part or part.lower() in _PAGE_SENTINELS:
+            continue
+        if "-" in part and part[0] != "-":
+            try:
+                lo, hi = part.split("-", 1)
+                result.extend(range(int(lo), int(hi) + 1))
+            except ValueError:
+                continue
+        else:
+            try:
+                result.append(int(part))
+            except ValueError:
+                continue
+    return result
+
+
+def row_page_set(row: dict) -> set[int]:
+    """Pull 0-based page indices from a CID row dict into a set."""
+    return set(parse_page_indices(row.get("page_location_indices", "")))
+
+
+# ── Pydantic models ───────────────────────────────────────────────────────────
+
+
+class CIRow(BaseModel):
+    """One row of a Content Index.
+
+    Pairs a framework disclosure with where it appears in the PDF.
+    ``page_location_text`` is verbatim; ``page_location_indices`` are resolved 0-based indices.
+    """
+
+    standard_id: str
+    disclosure_text: str = Field(default="")
+    disclosure_text_extracted: str = Field(default="")
+    page_location_text: str = Field(default="")
+    page_location_indices: list[int] = Field(default_factory=list)
+
+    @field_validator("standard_id")
+    @classmethod
+    def _normalize_sid(cls, v: str) -> str:
+        return normalize_standard_id(v)
+
+    @field_validator("page_location_indices", mode="before")
+    @classmethod
+    def _coerce_indices(cls, v: str | list[int]) -> list[int]:
+        return parse_page_indices(v)
+
+    @field_validator("page_location_text", mode="before")
+    @classmethod
+    def _coerce_text(cls, v) -> str:
+        if v is None:
+            return ""
+        if isinstance(v, list):
+            return ", ".join(str(x) for x in v if x is not None and str(x).strip())
+        return str(v).strip()
+
+
+class ContentIndex(BaseModel):
+    """A full Content Index for one PDF — one CIRow per framework disclosure."""
+
+    report_name: str
+    framework: str
+    num_disclosures: int = Field(ge=0)
+    ci_page_labels: str = Field(default="")
+    ci_page_indices: list[int] = Field(default_factory=list)
+    rows: list[CIRow]
+
+    @field_validator("ci_page_indices", mode="before")
+    @classmethod
+    def _coerce_ci_indices(cls, v: str | list[int]) -> list[int]:
+        return parse_page_indices(v)
+
+    @classmethod
+    def from_json_file(cls, path: str) -> ContentIndex:
+        with open(Path(path)) as f:
+            return cls.model_validate(json.load(f))
+
+    def to_json_file(self, path: str) -> None:
+        Path(path).parent.mkdir(parents=True, exist_ok=True)
+        with open(path, "w") as f:
+            json.dump(self.model_dump(), f, indent=2)
+
+    def to_cid_rows(self) -> list[dict]:
+        """Convert to a list of dicts matching the HuggingFace ``cid`` config schema."""
+        return [
+            {
+                "report_name": self.report_name,
+                "framework": self.framework,
+                "standard_id": r.standard_id,
+                "disclosure_text": r.disclosure_text,
+                "page_location_labels": r.page_location_text,
+                "page_location_indices": r.page_location_indices,
+            }
+            for r in self.rows
+        ]
+
+
+# ── Framework spec ────────────────────────────────────────────────────────────
+
+
+@dataclass(frozen=True)
+class DisclosureDef:
+    """Definition of a single disclosure from the official framework template."""
+
+    standard_id: str
+    title: str
+    parent_standard: str = ""
+
+
+@dataclass
+class FrameworkSpec:
+    """A reporting framework specification (loaded from HuggingFace).
+
+    ``group_pattern`` is a compiled regex that matches any standard_id
+    belonging to this framework — used by the page detector and drafter.
+    """
+
+    id: str
+    display_name: str
+    group_pattern: re.Pattern[str] | None = None
+    disclosures: dict[str, DisclosureDef] = field(default_factory=dict)
+
+    def has_disclosure(self, standard_id: str) -> bool:
+        return standard_id in self.disclosures
+
+    def get_title(self, standard_id: str) -> str | None:
+        d = self.disclosures.get(standard_id)
+        return d.title if d else None
+
+    def detect(self, standard_ids: list[str]) -> bool:
+        """Heuristic: do these IDs look like they belong to this framework?"""
+        if not standard_ids:
+            return False
+        matched = sum(1 for sid in standard_ids if sid in self.disclosures)
+        return matched / len(standard_ids) > 0.5