dirsql-plugin-embeddings 0.1.3__tar.gz → 0.1.5__tar.gz

{dirsql_plugin_embeddings-0.1.3 → dirsql_plugin_embeddings-0.1.5}/PKG-INFO

@@ -1,8 +1,9 @@
 Metadata-Version: 2.4
 Name: dirsql-plugin-embeddings
-Version: 0.1.3
+Version: 0.1.5
 Summary: First-party dirsql plugin: semantic search via an OpenAI-compatible embeddings endpoint.
-Requires-Python: >=3.11
+Requires-Python: >=3.10
+Requires-Dist: pypdf>=6
 Description-Content-Type: text/markdown
 
 # dirsql-plugin-embeddings

dirsql_plugin_embeddings-0.1.3/e2e-attestations/claude-on-file-integration-e2e-lpeicb-read-content.json → dirsql_plugin_embeddings-0.1.5/e2e-attestations/claude-699-read-pdf.json

@@ -1,7 +1,7 @@
 {
   "command": "uv run --with sqlite-vec --with-editable . --with-editable ../../packages/python python -m pytest tests/e2e -x -q",
-  "ran_at": 1785324484,
+  "ran_at": 1785327111,
   "exit_code": 0,
-  "commit": "e8600a3672b0ecd9c604c3c22ecc5be49adc5df5",
-  "branch": "claude/on-file-integration-e2e-lpeicb-read-content"
+  "commit": "b59ad4bf5dce929e2172cde15888918de9d277fd",
+  "branch": "claude/699-read-pdf"
 }

{dirsql_plugin_embeddings-0.1.3 → dirsql_plugin_embeddings-0.1.5}/pyproject.toml

@@ -11,7 +11,10 @@ name = "dirsql-plugin-embeddings"
 dynamic = ["version"]
 description = "First-party dirsql plugin: semantic search via an OpenAI-compatible embeddings endpoint."
 readme = "README.md"
-requires-python = ">=3.11"
+requires-python = ">=3.10"
+# pypdf, not pymupdf: pymupdf is AGPL-3.0, and a runtime dependency of this
+# MIT-licensed package propagates to everyone who installs it.
+dependencies = ["pypdf>=6"]
 
 [tool.hatch.version]
 source = "vcs"

dirsql_plugin_embeddings-0.1.5/src/dirsql_plugin_embeddings/on_file/read_pdf.py

@@ -0,0 +1,16 @@
+"""Extract a PDF's text.
+
+pypdf rather than pymupdf: pymupdf is AGPL-3.0, and a runtime dependency of
+this MIT-licensed package propagates to everyone who installs it.
+
+Annotations are evaluated at runtime (no ``from __future__ import
+annotations``) so a mutated ``X | None`` union in a signature fails at import
+rather than surviving as an inert string.
+"""
+
+from pypdf import PdfReader
+
+
+def read_pdf(path: str) -> str:
+    reader = PdfReader(path)
+    return "\n".join(page.extract_text() for page in reader.pages)