span-aligner 0.1.0__tar.gz

span_aligner-0.1.0/LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2026 Stefaan Vercoutere
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

span_aligner-0.1.0/PKG-INFO

@@ -0,0 +1,122 @@
+Metadata-Version: 2.4
+Name: span-aligner
+Version: 0.1.0
+Summary: A utility for aligning and mapping text spans between different text representations.
+License: MIT
+Requires-Python: >=3.8
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: rapidfuzz>=3.0.0
+Provides-Extra: dev
+Requires-Dist: pytest>=7.0.0; extra == "dev"
+Dynamic: license-file
+
+# Span Aligner
+
+A utility for aligning and mapping text spans between different text representations, particularly useful for Label Studio annotation compatibility.
+
+## Features
+
+- Sanitize span boundaries to avoid special characters.
+- Find exact and fuzzy matches of text segments in original documents.
+- Map spans from one text representation to another.
+- Rebuild tagged text with nested annotations.
+- Merge result objects containing span annotations.
+
+## Installation
+
+Install from source:
+
+```bash
+pip install .
+```
+
+For development:
+
+```bash
+pip install -e ".[dev]"
+```
+
+## Usage
+
+```python
+from span_aligner import SpanAligner
+
+original = "Hello, World!"
+result_obj = {
+    "spans": [{"start": 0, "end": 5, "text": "Hello", "labels": ["greeting"]}],
+    "entities": [],
+    "task": {"data": {"text": ""}}
+}
+
+success, mapped = SpanAligner.map_spans_to_original(original, result_obj)
+print(mapped)
+```
+
+### Map Tags to Original
+
+Align annotated spans from a tagged string back to their positions in the original text, keeping the mistakes and original text as written in the original.
+
+```python
+original_text = "The quick brown fox jumps\n\n over the dog."
+# Imagine the text was slightly modified or translated, but tags are present
+tagged_text = "The <adj>quick</adj> brown fox jumps over the <animal>dog</animal>."
+
+mapped_tagged_text = SpanAligner.map_tags_to_original(
+    original_text=original_text,
+    tagged_text=tagged_text,
+    min_ratio=0.8
+)
+print(mapped_tagged_text)
+# Output might look like: "The <adj>quick</adj> brown fox jumps\n\n over the <animal>dog</animal>."
+# (If original text differed slightly, tags would be placed on best matching spans)
+```
+
+### Rebuild Tagged Text
+
+Reconstruct a string with XML-like tags from raw text and span/entity lists.
+
+```python
+text = "Hello World"
+spans = [{"start": 0, "end": 11, "labels": ["sentence"]}]
+entities = [{"start": 6, "end": 11, "labels": ["location"]}]
+
+tagged, stats = SpanAligner.rebuild_tagged_text(text, spans, entities)
+print(tagged)
+# Output: <sentence>Hello <location>World</location></sentence>
+```
+
+### Rebuild Tagged Text from Task
+
+Generate tagged text directly from a Label Studio task object.
+
+```python
+# Assuming 'task' is a Label Studio task object (or similar structure)
+# with .data['text'] and .annotations attributes
+mapping = {"Location": "loc", "Person": "per"}
+
+tagged_output = SpanAligner.rebuild_tagged_text_from_task(task, mapping)
+print(tagged_output)
+```
+
+### Get Annotations from Tagged Text
+
+Extract structured spans and entities from a string with inline tags.
+
+```python
+tagged_input = "Visit <loc>Paris</loc> and see the <landmark>Eiffel Tower</landmark>."
+
+annotations = SpanAligner.get_annotations_from_tagged_text(
+    tagged_input,
+    ner_map={"loc": "Location", "landmark": "Location"}
+)
+
+print(annotations["entities"])
+# Output: 
+# [
+#   {"start": 6, "end": 11, "text": "Paris", "labels": ["Location"]},
+#   {"start": 24, "end": 36, "text": "Eiffel Tower", "labels": ["Location"]}
+# ]
+print(annotations["plain_text"])
+# Output: "Visit Paris and see the Eiffel Tower."
+```

span_aligner-0.1.0/README.md

@@ -0,0 +1,109 @@
+# Span Aligner
+
+A utility for aligning and mapping text spans between different text representations, particularly useful for Label Studio annotation compatibility.
+
+## Features
+
+- Sanitize span boundaries to avoid special characters.
+- Find exact and fuzzy matches of text segments in original documents.
+- Map spans from one text representation to another.
+- Rebuild tagged text with nested annotations.
+- Merge result objects containing span annotations.
+
+## Installation
+
+Install from source:
+
+```bash
+pip install .
+```
+
+For development:
+
+```bash
+pip install -e ".[dev]"
+```
+
+## Usage
+
+```python
+from span_aligner import SpanAligner
+
+original = "Hello, World!"
+result_obj = {
+    "spans": [{"start": 0, "end": 5, "text": "Hello", "labels": ["greeting"]}],
+    "entities": [],
+    "task": {"data": {"text": ""}}
+}
+
+success, mapped = SpanAligner.map_spans_to_original(original, result_obj)
+print(mapped)
+```
+
+### Map Tags to Original
+
+Align annotated spans from a tagged string back to their positions in the original text, keeping the mistakes and original text as written in the original.
+
+```python
+original_text = "The quick brown fox jumps\n\n over the dog."
+# Imagine the text was slightly modified or translated, but tags are present
+tagged_text = "The <adj>quick</adj> brown fox jumps over the <animal>dog</animal>."
+
+mapped_tagged_text = SpanAligner.map_tags_to_original(
+    original_text=original_text,
+    tagged_text=tagged_text,
+    min_ratio=0.8
+)
+print(mapped_tagged_text)
+# Output might look like: "The <adj>quick</adj> brown fox jumps\n\n over the <animal>dog</animal>."
+# (If original text differed slightly, tags would be placed on best matching spans)
+```
+
+### Rebuild Tagged Text
+
+Reconstruct a string with XML-like tags from raw text and span/entity lists.
+
+```python
+text = "Hello World"
+spans = [{"start": 0, "end": 11, "labels": ["sentence"]}]
+entities = [{"start": 6, "end": 11, "labels": ["location"]}]
+
+tagged, stats = SpanAligner.rebuild_tagged_text(text, spans, entities)
+print(tagged)
+# Output: <sentence>Hello <location>World</location></sentence>
+```
+
+### Rebuild Tagged Text from Task
+
+Generate tagged text directly from a Label Studio task object.
+
+```python
+# Assuming 'task' is a Label Studio task object (or similar structure)
+# with .data['text'] and .annotations attributes
+mapping = {"Location": "loc", "Person": "per"}
+
+tagged_output = SpanAligner.rebuild_tagged_text_from_task(task, mapping)
+print(tagged_output)
+```
+
+### Get Annotations from Tagged Text
+
+Extract structured spans and entities from a string with inline tags.
+
+```python
+tagged_input = "Visit <loc>Paris</loc> and see the <landmark>Eiffel Tower</landmark>."
+
+annotations = SpanAligner.get_annotations_from_tagged_text(
+    tagged_input,
+    ner_map={"loc": "Location", "landmark": "Location"}
+)
+
+print(annotations["entities"])
+# Output: 
+# [
+#   {"start": 6, "end": 11, "text": "Paris", "labels": ["Location"]},
+#   {"start": 24, "end": 36, "text": "Eiffel Tower", "labels": ["Location"]}
+# ]
+print(annotations["plain_text"])
+# Output: "Visit Paris and see the Eiffel Tower."
+```

span_aligner-0.1.0/pyproject.toml

@@ -0,0 +1,23 @@
+[build-system]
+requires = ["setuptools>=61.0"]
+build-backend = "setuptools.build_meta"
+
+[project]
+name = "span-aligner"
+version = "0.1.0"
+description = "A utility for aligning and mapping text spans between different text representations."
+readme = "README.md"
+requires-python = ">=3.8"
+license = {text = "MIT"}
+dependencies = [
+    "rapidfuzz>=3.0.0",
+]
+
+[project.optional-dependencies]
+dev = [
+    "pytest>=7.0.0",
+]
+
+[tool.setuptools.packages.find]
+where = ["."]
+include = ["span_aligner*"]

span_aligner-0.1.0/setup.cfg

@@ -0,0 +1,4 @@
+[egg_info]
+tag_build = 
+tag_date = 0
+

span_aligner-0.1.0/span_aligner/__init__.py

@@ -0,0 +1,3 @@
+from .aligner import SpanAligner
+
+__all__ = ["SpanAligner"]