echr-py 0.2.2__tar.gz → 0.2.3__tar.gz

{echr_py-0.2.2 → echr_py-0.2.3}/CITATION.cff

@@ -5,7 +5,7 @@ type: software
 authors:
   - family-names: Ridi
     given-names: Niccolo
-version: 0.2.2
+version: 0.2.3
 date-released: 2026-08-21
 license: MIT
 repository-code: "https://github.com/niccoloridi/echr-py"

{echr_py-0.2.2/echr_py.egg-info → echr_py-0.2.3}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: echr-py
-Version: 0.2.2
+Version: 0.2.3
 Summary: Pythonic acquisition of HUDOC and HUDOC-EXEC metadata and source documents for ECtHR research.
 Author-email: Niccolo Ridi <niccoloridi@gmail.com>
 License-Expression: MIT
@@ -102,7 +102,7 @@ Dynamic: license-file
   <a href="https://github.com/niccoloridi/echr-py/actions/workflows/ci.yml"><img src="https://github.com/niccoloridi/echr-py/actions/workflows/ci.yml/badge.svg" alt="CI"></a>
   <img src="https://img.shields.io/badge/python-3.11%E2%80%933.14-3776AB.svg" alt="Python 3.11–3.14">
   <a href="https://github.com/niccoloridi/echr-py/blob/main/LICENSE"><img src="https://img.shields.io/badge/license-MIT-green.svg" alt="MIT license"></a>
-  <img src="https://img.shields.io/badge/version-0.2.2-blue.svg" alt="Version 0.2.2">
+  <img src="https://img.shields.io/badge/version-0.2.3-blue.svg" alt="Version 0.2.3">
 </p>
 
 `echr-py` is a research engineering toolkit for the case law of the European
@@ -112,10 +112,6 @@ Court of Human Rights. It connects public
 research artifacts through Python, a command-line interface, and the Model
 Context Protocol (MCP).
 
-The distribution and primary command are now named `echr-py`. The established
-`hudoc_py` Python import and the legacy `hudoc-py` command remain available for
-backward compatibility.
-
 It is designed for work where provenance matters. A result can retain the exact
 HUDOC document, language version, section, paragraph, individual opinion,
 footnote, citation span, cited procedural document, cited-paragraph pinpoint,
@@ -495,7 +491,7 @@ without cloning the repository:
 
 ```bash
 claude mcp add --scope user --transport stdio echr-py -- \
-  "$(command -v uvx)" --from 'echr-py[mcp]==0.2.2' echr-py mcp
+  "$(command -v uvx)" --from 'echr-py[mcp]==0.2.3' echr-py mcp
 claude mcp get echr-py
 ```
 
@@ -635,6 +631,21 @@ cd echr-py
 python -m pip install -e ".[all,dev]"
 ```
 
+### Names
+
+The distribution and primary command are `echr-py`. The Python import is
+`hudoc_py`, and the earlier `hudoc-py` command still works; both remain
+available so existing code and scripts keep running.
+
+```python
+import hudoc_py            # import name
+```
+
+```bash
+echr-py --version          # primary command
+hudoc-py --version         # legacy alias, same program
+```
+
 ## Documentation
 
 - [Worked examples](https://github.com/niccoloridi/echr-py/blob/main/docs/examples.md)

{echr_py-0.2.2 → echr_py-0.2.3}/README.md

@@ -14,7 +14,7 @@
   <a href="https://github.com/niccoloridi/echr-py/actions/workflows/ci.yml"><img src="https://github.com/niccoloridi/echr-py/actions/workflows/ci.yml/badge.svg" alt="CI"></a>
   <img src="https://img.shields.io/badge/python-3.11%E2%80%933.14-3776AB.svg" alt="Python 3.11–3.14">
   <a href="https://github.com/niccoloridi/echr-py/blob/main/LICENSE"><img src="https://img.shields.io/badge/license-MIT-green.svg" alt="MIT license"></a>
-  <img src="https://img.shields.io/badge/version-0.2.2-blue.svg" alt="Version 0.2.2">
+  <img src="https://img.shields.io/badge/version-0.2.3-blue.svg" alt="Version 0.2.3">
 </p>
 
 `echr-py` is a research engineering toolkit for the case law of the European
@@ -24,10 +24,6 @@ Court of Human Rights. It connects public
 research artifacts through Python, a command-line interface, and the Model
 Context Protocol (MCP).
 
-The distribution and primary command are now named `echr-py`. The established
-`hudoc_py` Python import and the legacy `hudoc-py` command remain available for
-backward compatibility.
-
 It is designed for work where provenance matters. A result can retain the exact
 HUDOC document, language version, section, paragraph, individual opinion,
 footnote, citation span, cited procedural document, cited-paragraph pinpoint,
@@ -407,7 +403,7 @@ without cloning the repository:
 
 ```bash
 claude mcp add --scope user --transport stdio echr-py -- \
-  "$(command -v uvx)" --from 'echr-py[mcp]==0.2.2' echr-py mcp
+  "$(command -v uvx)" --from 'echr-py[mcp]==0.2.3' echr-py mcp
 claude mcp get echr-py
 ```
 
@@ -547,6 +543,21 @@ cd echr-py
 python -m pip install -e ".[all,dev]"
 ```
 
+### Names
+
+The distribution and primary command are `echr-py`. The Python import is
+`hudoc_py`, and the earlier `hudoc-py` command still works; both remain
+available so existing code and scripts keep running.
+
+```python
+import hudoc_py            # import name
+```
+
+```bash
+echr-py --version          # primary command
+hudoc-py --version         # legacy alias, same program
+```
+
 ## Documentation
 
 - [Worked examples](https://github.com/niccoloridi/echr-py/blob/main/docs/examples.md)

{echr_py-0.2.2 → echr_py-0.2.3/echr_py.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: echr-py
-Version: 0.2.2
+Version: 0.2.3
 Summary: Pythonic acquisition of HUDOC and HUDOC-EXEC metadata and source documents for ECtHR research.
 Author-email: Niccolo Ridi <niccoloridi@gmail.com>
 License-Expression: MIT
@@ -102,7 +102,7 @@ Dynamic: license-file
   <a href="https://github.com/niccoloridi/echr-py/actions/workflows/ci.yml"><img src="https://github.com/niccoloridi/echr-py/actions/workflows/ci.yml/badge.svg" alt="CI"></a>
   <img src="https://img.shields.io/badge/python-3.11%E2%80%933.14-3776AB.svg" alt="Python 3.11–3.14">
   <a href="https://github.com/niccoloridi/echr-py/blob/main/LICENSE"><img src="https://img.shields.io/badge/license-MIT-green.svg" alt="MIT license"></a>
-  <img src="https://img.shields.io/badge/version-0.2.2-blue.svg" alt="Version 0.2.2">
+  <img src="https://img.shields.io/badge/version-0.2.3-blue.svg" alt="Version 0.2.3">
 </p>
 
 `echr-py` is a research engineering toolkit for the case law of the European
@@ -112,10 +112,6 @@ Court of Human Rights. It connects public
 research artifacts through Python, a command-line interface, and the Model
 Context Protocol (MCP).
 
-The distribution and primary command are now named `echr-py`. The established
-`hudoc_py` Python import and the legacy `hudoc-py` command remain available for
-backward compatibility.
-
 It is designed for work where provenance matters. A result can retain the exact
 HUDOC document, language version, section, paragraph, individual opinion,
 footnote, citation span, cited procedural document, cited-paragraph pinpoint,
@@ -495,7 +491,7 @@ without cloning the repository:
 
 ```bash
 claude mcp add --scope user --transport stdio echr-py -- \
-  "$(command -v uvx)" --from 'echr-py[mcp]==0.2.2' echr-py mcp
+  "$(command -v uvx)" --from 'echr-py[mcp]==0.2.3' echr-py mcp
 claude mcp get echr-py
 ```
 
@@ -635,6 +631,21 @@ cd echr-py
 python -m pip install -e ".[all,dev]"
 ```
 
+### Names
+
+The distribution and primary command are `echr-py`. The Python import is
+`hudoc_py`, and the earlier `hudoc-py` command still works; both remain
+available so existing code and scripts keep running.
+
+```python
+import hudoc_py            # import name
+```
+
+```bash
+echr-py --version          # primary command
+hudoc-py --version         # legacy alias, same program
+```
+
 ## Documentation
 
 - [Worked examples](https://github.com/niccoloridi/echr-py/blob/main/docs/examples.md)

{echr_py-0.2.2 → echr_py-0.2.3}/hudoc_py/__init__.py

@@ -37,7 +37,7 @@ from ._sync import (
 from .main.dsl import Q
 from .models import Case, CaseCollection, Document, Sections
 
-__version__ = "0.2.2"
+__version__ = "0.2.3"
 
 __all__ = [
     "__version__",

{echr_py-0.2.2 → echr_py-0.2.3}/hudoc_py/bilingual/__init__.py

@@ -33,6 +33,7 @@ from .rescue import (
     find_french_sibling,
     rescue_candidates,
     rescue_french,
+    sibling_conflicts,
 )
 
 
@@ -70,6 +71,7 @@ __all__ = [
     "ReconcileStats",
     "ReconcileInvariantError",
     "rescue_french",
+    "sibling_conflicts",
     "rescue_candidates",
     "find_french_sibling",
     "apply_rescue_mapping",

{echr_py-0.2.2 → echr_py-0.2.3}/hudoc_py/bilingual/rescue.py

@@ -24,7 +24,7 @@ from __future__ import annotations
 
 import asyncio
 import logging
-from datetime import UTC, datetime
+from datetime import UTC, date, datetime
 from pathlib import Path
 from typing import Literal
 
@@ -86,6 +86,52 @@ def rescue_candidates(collection: list[Case]) -> list[Case]:
     return out
 
 
+def _case_date(case: Case) -> date | None:
+    """The document's own decision date, whichever HUDOC field carries it."""
+    return case.kp_date or case.judgement_date or case.decision_date
+
+
+def sibling_conflicts(case: Case, sibling: Case) -> list[str]:
+    """Reasons *sibling* cannot be the French counterpart of *case*.
+
+    An application number identifies an *application*, not a document. The same
+    number spans merits, just satisfaction, admissibility and revision
+    documents, so a sibling accepted on the number alone can silently pair an
+    English merits placeholder with a French admissibility decision.
+
+    Acceptance is therefore conjunctive and fail-closed: every identity the two
+    records both supply must agree. Evidence the sibling does not carry cannot
+    create a conflict, but it cannot excuse one either.
+    """
+    conflicts: list[str] = []
+
+    if case.doctype and sibling.doctype and case.doctype != sibling.doctype:
+        conflicts.append(f"doctype {case.doctype} != {sibling.doctype}")
+
+    if (
+        case.doctype_branch
+        and sibling.doctype_branch
+        and case.doctype_branch != sibling.doctype_branch
+    ):
+        conflicts.append(
+            f"doctype_branch {case.doctype_branch} != {sibling.doctype_branch}"
+        )
+
+    case_date, sibling_date = _case_date(case), _case_date(sibling)
+    if case_date and sibling_date and case_date != sibling_date:
+        conflicts.append(f"date {case_date.isoformat()} != {sibling_date.isoformat()}")
+
+    # A shared ECLI payload is the strongest available identity: the language
+    # segment differs between siblings, the rest must not.
+    if case.ecli and sibling.ecli and case.ecli != sibling.ecli:
+        conflicts.append(f"ecli {case.ecli} != {sibling.ecli}")
+
+    if case.appno and sibling.appno and not set(case.appno) & set(sibling.appno):
+        conflicts.append("no shared application number")
+
+    return conflicts
+
+
 async def find_french_sibling(
     client: AsyncHudocClient,
     case: Case,
@@ -98,7 +144,12 @@ async def find_french_sibling(
 
     Tries each application number in order; returns
     ``(french_itemid, appno_used, appnos_tried)`` for the first appno that
-    yields a non-placeholder French document distinct from ``case.itemid``.
+    yields a non-placeholder French document distinct from ``case.itemid``
+    **and compatible with it** under :func:`sibling_conflicts`.
+
+    A candidate whose doctype, branch, date, ECLI or application set conflicts
+    is skipped rather than returned, so a run abstains instead of pairing an
+    English placeholder with the wrong procedural document.
     """
     tried: list[str] = []
     for appno in case.appno:
@@ -118,6 +169,15 @@ async def find_french_sibling(
                 continue
             if sibling.is_placeholder is True:
                 continue
+            conflicts = sibling_conflicts(case, sibling)
+            if conflicts:
+                logger.debug(
+                    "rescue: rejected %s for %s (%s)",
+                    sibling.itemid,
+                    case.itemid,
+                    "; ".join(conflicts),
+                )
+                continue
             return sibling.itemid, appno, tried
     return None, None, tried
 

{echr_py-0.2.2 → echr_py-0.2.3}/hudoc_py/text/opinions.py

@@ -66,6 +66,13 @@ _EN_CONTINUATION_RE = re.compile(
     re.VERBOSE,
 )
 
+# Legacy conversions lowercase the names tail. Matched only through
+# :func:`_continuation_names`, which requires roster anchoring for that form.
+_EN_CONTINUATION_LOWER_RE = re.compile(
+    rf"^\s*(?:OF\s+)?(?:{_EN_TITLE})?(?P<names>\w.*?)\s*$",
+    re.VERBOSE | re.IGNORECASE,
+)
+
 # --- French heading grammar --------------------------------------------------
 
 _FR_TYPE = r"""
@@ -238,8 +245,14 @@ def _classify_fr(type_full: str) -> OpinionType:
 def _looks_like_heading_tail(names: str) -> bool:
     """Accept a title-case heading but reject a sentence-shaped names tail."""
     tail = names.strip()
-    if not tail or len(tail) >= 90 or tail.endswith((".", ";", ":")):
+    if not tail or tail.endswith((".", ";", ":")):
         return False
+    # The length ceiling separates a names tail from a wrapped prose sentence.
+    # A joint opinion of six or more judges legitimately exceeds it, so an
+    # over-long tail is not rejected outright: it must clear the roster anchor
+    # below, which prose cannot.
+    if len(tail) >= 90:
+        return _names_all_rostered(tail)
     # A proper name may be title case and contain connectors/particles, but a
     # prose continuation contains other wholly lowercase words.
     without_name_words = re.sub(
@@ -248,7 +261,31 @@ def _looks_like_heading_tail(names: str) -> bool:
         tail,
         flags=re.IGNORECASE,
     )
-    return re.search(r"\b[a-zà-ÿ]{3,}\b", without_name_words) is None
+    if re.search(r"\b[a-zà-ÿ]{3,}\b", without_name_words) is None:
+        return True
+    # Legacy HUDOC conversions lowercase an otherwise exact names tail, which
+    # is indistinguishable from prose by casing alone. Accept that form only
+    # when every parsed name is independently anchored in the verified
+    # elected/ad-hoc roster, exactly as :func:`_heading_case_allowed` does for
+    # a lowercased single-line heading. Prose tails still fail closed.
+    return _names_all_rostered(tail)
+
+
+def _names_all_rostered(tail: str) -> bool:
+    """True when every name in *tail* resolves in the canonical judge roster."""
+    from .judges import is_ad_hoc_judge, judge_country
+
+    stripped = re.sub(
+        r"^\s*(?:of|by|des|du|de)\s+(?:the\s+)?(?:judges?|juges?|mr|mrs|ms|sir)\b\.?\s*",
+        "",
+        tail,
+        flags=re.IGNORECASE,
+    )
+    authors, joined_by = _split_authors_joiners(stripped)
+    judges = [*authors, *joined_by]
+    return bool(judges) and all(
+        judge_country(judge) is not None or is_ad_hoc_judge(judge) for judge in judges
+    )
 
 
 def _heading_case_allowed(prefix: str, names: str) -> bool:
@@ -300,6 +337,24 @@ def _extend_names(lines: list[str], names: str, end: int, connectors: str) -> tu
     return names, end
 
 
+
+def _continuation_names(strict: re.Pattern[str], lenient: re.Pattern[str], line: str) -> str | None:
+    """Names from a heading continuation line, or ``None``.
+
+    The strict pattern carries the ordinary uppercase contract. The lenient
+    pattern additionally accepts a lowercased tail, which legacy HUDOC
+    conversions produce, but only when every parsed name is anchored in the
+    verified elected/ad-hoc roster.
+    """
+    match = strict.match(line)
+    if match:
+        return match.group("names")
+    match = lenient.match(line)
+    if match and _names_all_rostered(match.group("names")):
+        return match.group("names")
+    return None
+
+
 def _match_header(lines: list[str], i: int) -> _Header | None:
     line = lines[i].strip()
     if not line or _TOC_LINE_RE.search(line):
@@ -344,11 +399,11 @@ def _match_header(lines: list[str], i: int) -> _Header | None:
     continuation = _next_continuation(lines, i) if match else None
     if match and continuation:
         j, continuation_line = continuation
-        cont = _EN_CONTINUATION_RE.match(continuation_line)
-        if cont and _heading_case_allowed(line, cont.group("names")):
-            names, end = _extend_names(
-                lines, cont.group("names"), j + 1, r"(?:,|\bAND)\s*$"
-            )
+        cont_names = _continuation_names(
+            _EN_CONTINUATION_RE, _EN_CONTINUATION_LOWER_RE, continuation_line
+        )
+        if cont_names is not None and _heading_case_allowed(line, cont_names):
+            names, end = _extend_names(lines, cont_names, j + 1, r"(?:,|\bAND)\s*$")
             return _Header(
                 i,
                 end,

{echr_py-0.2.2 → echr_py-0.2.3}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "echr-py"
-version = "0.2.2"
+version = "0.2.3"
 description = "Pythonic acquisition of HUDOC and HUDOC-EXEC metadata and source documents for ECtHR research."
 readme = "README.md"
 requires-python = ">=3.11"