docslicer 0.2.2__tar.gz → 0.2.3__tar.gz

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

@@ -1,7 +1,7 @@
 Metadata-Version: 2.4
 Name: docslicer
-Version: 0.2.2
-Summary: Deterministic hierarchical document parser and chunker
+Version: 0.2.3
+Summary: Answer questions from documents too large to fit in context, reading only the sections you need
 Author-email: "Market Framer Inc." <jelle@docslicer.ai>
 License-Expression: AGPL-3.0-only
 Project-URL: Homepage, https://docslicer.ai

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

@@ -4,8 +4,8 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "docslicer"
-version = "0.2.2"
-description = "Deterministic hierarchical document parser and chunker"
+version = "0.2.3"
+description = "Answer questions from documents too large to fit in context, reading only the sections you need"
 readme = "README.md"
 license = "AGPL-3.0-only"
 license-files = ["LICENSE"]

{docslicer-0.2.2 → docslicer-0.2.3}/src/docslicer/_result.py

@@ -1110,7 +1110,8 @@ class ParseResult:
             if self.charts:
                 _to_parquet(self.charts_df(), path / "charts.parquet")
             (path / "metadata.json").write_text(
-                json.dumps(self.metadata.to_dict(), indent=2, ensure_ascii=False)
+                json.dumps(self.metadata.to_dict(), indent=2, ensure_ascii=False),
+                encoding="utf-8",
             )
             return
 
@@ -1129,20 +1130,29 @@ class ParseResult:
         if stem == "metadata":
             if suffix != ".json":
                 raise ValueError("metadata can only be saved as .json")
-            path.write_text(json.dumps(self.metadata.to_dict(), indent=2, ensure_ascii=False))
+            path.write_text(
+                json.dumps(self.metadata.to_dict(), indent=2, ensure_ascii=False),
+                encoding="utf-8",
+            )
             return
 
         # Unknown stem (e.g. "result") → full document export
         if stem not in level_map:
             if suffix != ".json":
                 raise ValueError(f"Unknown stem {stem!r}: use chunks/blocks/tables/charts/metadata, or a .json path for a full export")
-            path.write_text(json.dumps(self.to_dict(), indent=2, ensure_ascii=False))
+            path.write_text(
+                json.dumps(self.to_dict(), indent=2, ensure_ascii=False),
+                encoding="utf-8",
+            )
             return
 
         rows_fn = level_map[stem]
 
         if suffix == ".json":
-            path.write_text(json.dumps(rows_fn(), indent=2, ensure_ascii=False))
+            path.write_text(
+                json.dumps(rows_fn(), indent=2, ensure_ascii=False),
+                encoding="utf-8",
+            )
         elif suffix == ".jsonl":
             with path.open("w", encoding="utf-8") as f:
                 for row in rows_fn():

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

@@ -1,7 +1,7 @@
 Metadata-Version: 2.4
 Name: docslicer
-Version: 0.2.2
-Summary: Deterministic hierarchical document parser and chunker
+Version: 0.2.3
+Summary: Answer questions from documents too large to fit in context, reading only the sections you need
 Author-email: "Market Framer Inc." <jelle@docslicer.ai>
 License-Expression: AGPL-3.0-only
 Project-URL: Homepage, https://docslicer.ai

{docslicer-0.2.2 → docslicer-0.2.3}/src/docslicer.egg-info/SOURCES.txt

@@ -1,5 +1,4 @@
 LICENSE
-LICENSE-COMMERCIAL.md
 README.md
 pyproject.toml
 src/docslicer/__init__.py

{docslicer-0.2.2 → docslicer-0.2.3}/tests/test_charts.py

@@ -85,7 +85,7 @@ def test_export_charts_csv(pptx_result, tmp_path):
     path = tmp_path / "charts.csv"
     pptx_result.export_charts_csv(path)
     assert path.exists()
-    lines = path.read_text().splitlines()
+    lines = path.read_text(encoding="utf-8").splitlines()
     # header + one row per datapoint
     assert len(lines) == 1 + sum(len(c.points) for c in pptx_result.charts)
 

{docslicer-0.2.2 → docslicer-0.2.3}/tests/test_exports.py

@@ -65,7 +65,7 @@ def test_export_chunks_jsonl(pdf_result, tmp_path):
     path = tmp_path / "chunks.jsonl"
     pdf_result.export_chunks_jsonl(path)
     assert path.exists()
-    lines = path.read_text().splitlines()
+    lines = path.read_text(encoding="utf-8").splitlines()
     assert len(lines) == len(pdf_result.chunks)
     assert json.loads(lines[0])["id"] == pdf_result.chunks[0].id
 
@@ -102,7 +102,7 @@ def test_hierarchy_save(pdf_result, tmp_path):
     path = tmp_path / "hierarchy.json"
     pdf_result.hierarchy.save(path)
     assert path.exists()
-    data = json.loads(path.read_text())
+    data = json.loads(path.read_text(encoding="utf-8"))
     assert isinstance(data, list)
 
 
@@ -110,7 +110,7 @@ def test_hierarchy_save_minimal(pdf_result, tmp_path):
     path = tmp_path / "hierarchy_minimal.json"
     pdf_result.hierarchy.save(path, minimal=True)
     assert path.exists()
-    data = json.loads(path.read_text())
+    data = json.loads(path.read_text(encoding="utf-8"))
     assert isinstance(data, list)
     if data:
         assert set(data[0].keys()) <= {"text", "children"}
@@ -120,7 +120,7 @@ def test_hierarchy_save_outline(pdf_result, tmp_path):
     path = tmp_path / "outline.md"
     pdf_result.hierarchy.save_outline(path)
     assert path.exists()
-    content = path.read_text()
+    content = path.read_text(encoding="utf-8")
     assert isinstance(content, str)
 
 

docslicer-0.2.2/LICENSE-COMMERCIAL.md

@@ -1,29 +0,0 @@
-# Licensing
-
-Docslicer is dual-licensed.
-
-## Open source — AGPL v3.0
-
-Docslicer is available under the GNU Affero General Public License v3.0
-(see LICENSE). You are free to use, modify, and distribute it under the
-AGPL, provided you comply with its terms — including making the complete
-source of any application that uses Docslicer available to its users,
-including over a network.
-
-## Commercial license
-
-If you cannot or do not want to comply with the AGPL, a commercial license
-is available. You likely need one if you want to:
-
-- embed Docslicer in a closed-source or proprietary product;
-- offer Docslicer's functionality as part of a hosted or SaaS service
-  without releasing your source; or
-- distribute Docslicer without AGPL obligations.
-
-The commercial license removes the AGPL's copyleft requirements and can
-include priority support, warranty, and IP indemnification.
-
-Unless you hold a separate signed commercial agreement, your use of
-Docslicer is governed by the AGPL.
-
-Contact **jelle@docslicer.ai** for commercial terms.