mmif-python 1.5.1__tar.gz → 1.5.2__tar.gz

{mmif_python-1.5.1 → mmif_python-1.5.2}/CHANGELOG.md

@@ -1,4 +1,9 @@
 
+## releasing 1.5.1 (2026-06-19)
+### Overview
+This patch contains a bug fix in VDH that couldn't handle some mkv-contained video files (https://github.com/clamsproject/mmif-python/issues/390) , and some other minor documentation generation bugs.
+
+
 ## releasing 1.5.0 (2026-05-27)
 ### Overview
 

{mmif_python-1.5.1 → mmif_python-1.5.2}/CONTRIBUTING.md

@@ -162,7 +162,7 @@ To build documentation for a specific historical version (e.g., `v1.0.0`):
 python3 build-tools/docs.py --build-ver v1.0.0
 ```
 
-This runs the build in a sandboxed temporary directory. The output will be in `docs-test/<version>`.
+This runs the build in a sandboxed temporary directory. A single `--build-ver` places the built docs **flat** in the output directory (`docs-test/` by default). The batch `--build-all-since` mode instead nests each version under a `<version>/` subdirectory of the output directory, so multiple versions can coexist. The flat single-version layout is what the CI docs-publish workflow relies on — it invokes `docs.py --build-ver <ver> --output-dir _docs` and uploads `_docs/` as-is, without needing to know whether the project is versioned.
 
 > [!NOTE]
 > In CI, documentation is built and published automatically by the `publish.yml` workflow via the shared `sdk-docs.yml`. The CI calls `docs.py --build-ver <version> --output-dir _docs`. All CLAMS SDK repos use the same `docs.py` CLI interface (`--build-ver`, `--output-dir`).

{mmif_python-1.5.1 → mmif_python-1.5.2}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: mmif-python
-Version: 1.5.1
+Version: 1.5.2
 Summary: Python implementation of MultiMedia Interchange Format specification. (https://mmif.clams.ai)
 License-Expression: Apache-2.0
 Project-URL: homepage, https://mmif.clams.ai

{mmif_python-1.5.1 → mmif_python-1.5.2}/build-tools/docs.py

@@ -188,7 +188,8 @@ def linkcode_resolve(domain, info):
     return docs_build_dir
 
 
-def build_docs_for_version(version: str, output_base_dir: Path, repo_path: Path = None):
+def build_docs_for_version(version: str, output_base_dir: Path, repo_path: Path = None,
+                           versioned_subdir: bool = True):
     """
     Builds docs for a specific version in a sandbox.
     Uses local repo copy instead of cloning for efficiency.
@@ -197,6 +198,12 @@ def build_docs_for_version(version: str, output_base_dir: Path, repo_path: Path
         version: Git tag/ref to build
         output_base_dir: Directory to output built docs
         repo_path: Path to local repo to copy from (defaults to cwd)
+        versioned_subdir: when True (batch/from-scratch rebuild), the built
+            docs are placed under ``output_base_dir/<version>/`` so multiple
+            versions can coexist. When False (single build, as used by CI),
+            the docs are placed flat into ``output_base_dir`` so the shared
+            docs-publish workflow can upload them as-is without knowing about
+            versioning.
     """
     print(f"--- Running in Version Build Mode for version: {version} ---")
 
@@ -226,13 +233,19 @@ def build_docs_for_version(version: str, output_base_dir: Path, repo_path: Path
         built_docs_path = build_versioned_docs(env, source_path, version)
 
         print(f"\n--- Step 4: Copying built artifacts to output directory ---")
-        version_output_dir = output_base_dir / version
-        if version_output_dir.exists():
-            print(f"Removing existing directory: {version_output_dir}")
-            shutil.rmtree(version_output_dir)
-        shutil.copytree(built_docs_path, version_output_dir)
+        if versioned_subdir:
+            dest = output_base_dir / version
+            if dest.exists():
+                print(f"Removing existing directory: {dest}")
+                shutil.rmtree(dest)
+            shutil.copytree(built_docs_path, dest)
+        else:
+            # flat: place the built docs directly into output_base_dir
+            output_base_dir.mkdir(parents=True, exist_ok=True)
+            shutil.copytree(built_docs_path, output_base_dir, dirs_exist_ok=True)
+            dest = output_base_dir
 
-        print(f"\nDocumentation for {version} built successfully in: {version_output_dir}")
+        print(f"\nDocumentation for {version} built successfully in: {dest}")
 
 
 def get_all_tags():
@@ -317,7 +330,9 @@ def main():
             for version, error in failed:
                 print(f"  {version}: {error}")
     elif args.build_ver:
-        build_docs_for_version(args.build_ver, output_dir)
+        # single build (CI + local single-version): flat output so the
+        # shared docs-publish workflow uploads it version-agnostically
+        build_docs_for_version(args.build_ver, output_dir, versioned_subdir=False)
     else:
         build_docs_local(Path.cwd(), output_dir)
 

{mmif_python-1.5.1 → mmif_python-1.5.2}/documentation/target-versions.csv

@@ -1,4 +1,5 @@
 "``mmif-python`` version","Target MMIF Specification"
+`1.5.2 <https://pypi.org/project/mmif-python/1.5.2/>`__,`1.2.0 <https://mmif.clams.ai/1.2.0/>`__
 `1.5.1 <https://pypi.org/project/mmif-python/1.5.1/>`__,`1.2.0 <https://mmif.clams.ai/1.2.0/>`__
 `1.5.0 <https://pypi.org/project/mmif-python/1.5.0/>`__,`1.2.0 <https://mmif.clams.ai/1.2.0/>`__
 `1.4.0 <https://pypi.org/project/mmif-python/1.4.0/>`__,`1.1.1 <https://mmif.clams.ai/1.1.1/>`__

{mmif_python-1.5.1 → mmif_python-1.5.2}/mmif/serialize/view.py

@@ -82,6 +82,25 @@ class View(MmifObject):
         self._required_attributes = ["id", "metadata", "annotations"]
         super().__init__(view_obj)
         self._fix_old_short_ids()
+        self._rebuild_id_counts()
+
+    def _rebuild_id_counts(self):
+        """
+        Re-seed the per-view auto-ID counters from the annotations loaded during
+        deserialization.
+
+        ``_id_counts`` is not serialized, so a view read back from JSON starts
+        with an empty counter. Without this, the next :meth:`new_annotation`
+        regenerates an ID (e.g. ``an_1``) that already exists in the
+        deserialized view and :meth:`AnnotationsList.append` raises ``KeyError``.
+        See issue #393.
+        """
+        for annotation in self.annotations:
+            local_id = annotation.id.split(self.id_delimiter)[-1]
+            prefix, _, num = local_id.rpartition('_')
+            if prefix and num.isdigit():
+                self._id_counts[prefix] = max(
+                    self._id_counts.get(prefix, 0), int(num))
 
     def _fix_old_short_ids(self):
         """

{mmif_python-1.5.1 → mmif_python-1.5.2}/mmif_python.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: mmif-python
-Version: 1.5.1
+Version: 1.5.2
 Summary: Python implementation of MultiMedia Interchange Format specification. (https://mmif.clams.ai)
 License-Expression: Apache-2.0
 Project-URL: homepage, https://mmif.clams.ai

{mmif_python-1.5.1 → mmif_python-1.5.2}/mmif_python.egg-info/SOURCES.txt

@@ -63,6 +63,8 @@ mmif_python.egg-info/SOURCES.txt
 mmif_python.egg-info/dependency_links.txt
 mmif_python.egg-info/entry_points.txt
 mmif_python.egg-info/requires.txt
+mmif_python.egg-info/scm_file_list.json
+mmif_python.egg-info/scm_version.json
 mmif_python.egg-info/top_level.txt
 tests/black-2997fps.mp4
 tests/black-2997fps.webm

mmif_python-1.5.2/mmif_python.egg-info/scm_file_list.json

@@ -0,0 +1,95 @@
+{
+  "files": [
+    "README.md",
+    "LICENSE",
+    "pyproject.toml",
+    "CHANGELOG.md",
+    "CONTRIBUTING.md",
+    ".gitignore",
+    "build-tools/publish.py",
+    "build-tools/prep_release.py",
+    "build-tools/build.py",
+    "build-tools/docs.py",
+    "build-tools/clean.py",
+    "build-tools/test.py",
+    "documentation/target-versions.csv",
+    "documentation/consumer-tutorial.rst",
+    "documentation/target-versions.rst",
+    "documentation/index.rst",
+    "documentation/introduction.rst",
+    "documentation/cli.rst",
+    "documentation/plugins.rst",
+    "documentation/summarizer.rst",
+    "documentation/conf.py",
+    "documentation/_mmif_example_builder/__init__.py",
+    "documentation/_templates/versions.html",
+    "mmif/__init__.py",
+    "mmif/vocabulary/__init__.py",
+    "mmif/vocabulary/base_types.py",
+    "mmif/vocabulary/document_types.py",
+    "mmif/vocabulary/annotation_types.py",
+    "mmif/utils/__init__.py",
+    "mmif/utils/text_document_helper.py",
+    "mmif/utils/timeunit_helper.py",
+    "mmif/utils/workflow_helper.py",
+    "mmif/utils/video_document_helper.py",
+    "mmif/utils/sequence_helper.py",
+    "mmif/utils/summarizer/__init__.py",
+    "mmif/utils/summarizer/config.py",
+    "mmif/utils/summarizer/utils.py",
+    "mmif/utils/summarizer/summary.py",
+    "mmif/utils/summarizer/graph.py",
+    "mmif/utils/summarizer/nodes.py",
+    "mmif/utils/cli/__init__.py",
+    "mmif/utils/cli/source.py",
+    "mmif/utils/cli/rewind.py",
+    "mmif/utils/cli/summarize.py",
+    "mmif/utils/cli/describe.py",
+    "mmif/serialize/model.py",
+    "mmif/serialize/__init__.py",
+    "mmif/serialize/view.py",
+    "mmif/serialize/annotation.py",
+    "mmif/serialize/mmif.py",
+    "mmif/res/__init__.py",
+    "mmif/res/mmif.json",
+    "mmif/ver/__init__.py",
+    "tests/mmif_examples.py",
+    "tests/test_specver.py",
+    "tests/test_utils.py",
+    "tests/test_utils_cli.py",
+    "tests/test_vocab.py",
+    "tests/testsrc-2997fps-ptsoffset.mp4",
+    "tests/test_serialize.py",
+    "tests/black-2997fps.mp4",
+    "tests/black-2997fps.webm",
+    "tests/mmif-examples/README.md",
+    "tests/mmif-examples/examples.json",
+    "tests/mmif-examples/1.0.5-old-shortid.json",
+    "tests/mmif-examples/swt-1.0.mmif",
+    "tests/mmif-examples/segmenter-kaldi-ner/raw.json",
+    "tests/mmif-examples/everything/raw.json",
+    "tests/mmif-examples/others/video-transcript.json",
+    "tests/mmif-examples/others/image-box-ocr-timex.json",
+    "tests/mmif-examples/others/README.md",
+    "tests/mmif-examples/others/video.json",
+    "tests/mmif-examples/others/video-transcript-demux-fa.json",
+    "tests/mmif-examples/others/image.json",
+    "tests/mmif-examples/others/video-transcript-sentencesplit.json",
+    "tests/mmif-examples/others/video-transcript-demux-fa.short.json",
+    "tests/mmif-examples/others/slate-detect.json",
+    "tests/mmif-examples/others/image-box.json",
+    "tests/mmif-examples/others/slate-reco.json",
+    "tests/mmif-examples/others/video-transcript-demux.json",
+    "tests/mmif-examples/others/image-box-ocr.json",
+    "tests/mmif-examples/others/video-demux.json",
+    "tests/mmif-examples/bars-tones-slates/raw.json",
+    "tests/mmif-examples/east-tesseract-typing/raw.json",
+    "mmif_docloc_http/__init__.py",
+    ".github/workflows/issue-close.yml",
+    ".github/workflows/codecov.yml",
+    ".github/workflows/release-check.yml",
+    ".github/workflows/issue-infra-project.yml",
+    ".github/workflows/issue-assign.yml",
+    ".github/workflows/publish.yml"
+  ]
+}

mmif_python-1.5.2/mmif_python.egg-info/scm_version.json

@@ -0,0 +1,8 @@
+{
+  "tag": "1.5.2",
+  "distance": 0,
+  "node": "g1b794b4741b27b9999c5cd9fec00d46bef6d5d8e",
+  "dirty": false,
+  "branch": "HEAD",
+  "node_date": "2026-07-07"
+}

{mmif_python-1.5.1 → mmif_python-1.5.2}/tests/test_serialize.py

@@ -1451,7 +1451,57 @@ class TestDocument(unittest.TestCase):
             'author'))
         self.assertEqual('you', list(mmif_roundtrip2.views.get_last_contentful_view().get_annotations(AnnotationTypes.Annotation))[
             0].get_property('author'))
-        
+
+    def test_view_id_counts_rebuilt_on_deserialize(self):
+        # regression for issue #393: `_id_counts` is not serialized, so after
+        # deserialization the next generated id must not collide with an existing
+        # one already present in the view.
+        mmif = Mmif(validate=False)
+        doc = Document(); doc.at_type = DocumentTypes.VideoDocument
+        doc.id = 'd1'; doc.location = 'file:///v.mp4'
+        mmif.add_document(doc)
+        v = mmif.new_view()
+        v.metadata.app = tester_appname
+        a1 = v.new_annotation(AnnotationTypes.Annotation, document='d1', frameCount=10)
+        self.assertTrue(a1.id.endswith('an_1'))
+        # round-trip: the reloaded view still contains `an_1` but starts with an
+        # empty counter unless rebuilt
+        v2 = Mmif(mmif.serialize())[v.id]
+        a2 = v2.new_annotation(AnnotationTypes.Annotation, document='d1', duration=20)
+        self.assertTrue(a2.id.endswith('an_2'))   # must not regenerate an_1
+
+    def test_capital_annotation_no_collision_across_apps(self):
+        # regression for issue #393: a downstream app re-deriving a document
+        # property with a *different* value must not crash on serialize; the
+        # distinct value is recorded as an additional capital annotation
+        # (value-based de-dup preserves both assertions), not a colliding one.
+        m = Mmif(validate=False)
+        d = Document()
+        d.at_type = DocumentTypes.VideoDocument
+        d.id = 'd1'
+        d.location = 'file:///v.mp4'
+        m.add_document(d)
+        v1 = m.new_view(); v1.metadata.app = 'http://app/producer'
+        v1.new_annotation(AnnotationTypes.TimeFrame, label='bars')
+        d.add_property('frameCount', 51248.0)
+        d.add_property('duration', 1709977.0)
+
+        # downstream app loads it and re-derives a *different* duration value
+        m2 = Mmif(m.serialize())
+        d2 = m2['d1']
+        v2 = m2.new_view(); v2.metadata.app = 'http://app/consumer'
+        v2.new_annotation(AnnotationTypes.TimeFrame, label='caption')
+        d2.add_property('frameCount', 51248)      # same value -> de-duped away
+        d2.add_property('duration', 1709975)      # different value -> new annotation
+        out = Mmif(m2.serialize())                # must not raise KeyError
+
+        caps = [a for view in out.views
+                for a in view.get_annotations(AnnotationTypes.Annotation)]
+        durations = {a.get_property('duration') for a in caps if 'duration' in a}
+        # both distinct duration assertions coexist; neither is lost or overwritten
+        self.assertEqual(2, len(caps))
+        self.assertEqual({1709977.0, 1709975}, durations)
+
     def test_capital_annotation_generation_viewfinder(self):
         mmif = Mmif(validate=False)
         for i in range(1, 3):