langidentify 1.0.0__tar.gz

langidentify-1.0.0/LICENSE

@@ -0,0 +1,201 @@
+                                 Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+   1. Definitions.
+
+      "License" shall mean the terms and conditions for use, reproduction,
+      and distribution as defined by Sections 1 through 9 of this document.
+
+      "Licensor" shall mean the copyright owner or entity authorized by
+      the copyright owner that is granting the License.
+
+      "Legal Entity" shall mean the union of the acting entity and all
+      other entities that control, are controlled by, or are under common
+      control with that entity. For the purposes of this definition,
+      "control" means (i) the power, direct or indirect, to cause the
+      direction or management of such entity, whether by contract or
+      otherwise, or (ii) ownership of fifty percent (50%) or more of the
+      outstanding shares, or (iii) beneficial ownership of such entity.
+
+      "You" (or "Your") shall mean an individual or Legal Entity
+      exercising permissions granted by this License.
+
+      "Source" form shall mean the preferred form for making modifications,
+      including but not limited to software source code, documentation
+      source, and configuration files.
+
+      "Object" form shall mean any form resulting from mechanical
+      transformation or translation of a Source form, including but
+      not limited to compiled object code, generated documentation,
+      and conversions to other media types.
+
+      "Work" shall mean the work of authorship, whether in Source or
+      Object form, made available under the License, as indicated by a
+      copyright notice that is included in or attached to the work
+      (an example is provided in the Appendix below).
+
+      "Derivative Works" shall mean any work, whether in Source or Object
+      form, that is based on (or derived from) the Work and for which the
+      editorial revisions, annotations, elaborations, or other modifications
+      represent, as a whole, an original work of authorship. For the purposes
+      of this License, Derivative Works shall not include works that remain
+      separable from, or merely link (or bind by name) to the interfaces of,
+      the Work and Derivative Works thereof.
+
+      "Contribution" shall mean any work of authorship, including
+      the original version of the Work and any modifications or additions
+      to that Work or Derivative Works thereof, that is intentionally
+      submitted to Licensor for inclusion in the Work by the copyright owner
+      or by an individual or Legal Entity authorized to submit on behalf of
+      the copyright owner. For the purposes of this definition, "submitted"
+      means any form of electronic, verbal, or written communication sent
+      to the Licensor or its representatives, including but not limited to
+      communication on electronic mailing lists, source code control systems,
+      and issue tracking systems that are managed by, or on behalf of, the
+      Licensor for the purpose of discussing and improving the Work, but
+      excluding communication that is conspicuously marked or otherwise
+      designated in writing by the copyright owner as "Not a Contribution."
+
+      "Contributor" shall mean Licensor and any individual or Legal Entity
+      on behalf of whom a Contribution has been received by Licensor and
+      subsequently incorporated within the Work.
+
+   2. Grant of Copyright License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      copyright license to reproduce, prepare Derivative Works of,
+      publicly display, publicly perform, sublicense, and distribute the
+      Work and such Derivative Works in Source or Object form.
+
+   3. Grant of Patent License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      (except as stated in this section) patent license to make, have made,
+      use, offer to sell, sell, import, and otherwise transfer the Work,
+      where such license applies only to those patent claims licensable
+      by such Contributor that are necessarily infringed by their
+      Contribution(s) alone or by combination of their Contribution(s)
+      with the Work to which such Contribution(s) was submitted. If You
+      institute patent litigation against any entity (including a
+      cross-claim or counterclaim in a lawsuit) alleging that the Work
+      or a Contribution incorporated within the Work constitutes direct
+      or contributory patent infringement, then any patent licenses
+      granted to You under this License for that Work shall terminate
+      as of the date such litigation is filed.
+
+   4. Redistribution. You may reproduce and distribute copies of the
+      Work or Derivative Works thereof in any medium, with or without
+      modifications, and in Source or Object form, provided that You
+      meet the following conditions:
+
+      (a) You must give any other recipients of the Work or
+          Derivative Works a copy of this License; and
+
+      (b) You must cause any modified files to carry prominent notices
+          stating that You changed the files; and
+
+      (c) You must retain, in the Source form of any Derivative Works
+          that You distribute, all copyright, patent, trademark, and
+          attribution notices from the Source form of the Work,
+          excluding those notices that do not pertain to any part of
+          the Derivative Works; and
+
+      (d) If the Work includes a "NOTICE" text file as part of its
+          distribution, then any Derivative Works that You distribute must
+          include a readable copy of the attribution notices contained
+          within such NOTICE file, excluding those notices that do not
+          pertain to any part of the Derivative Works, in at least one
+          of the following places: within a NOTICE text file distributed
+          as part of the Derivative Works; within the Source form or
+          documentation, if provided along with the Derivative Works; or,
+          within a display generated by the Derivative Works, if and
+          wherever such third-party notices normally appear. The contents
+          of the NOTICE file are for informational purposes only and
+          do not modify the License. You may add Your own attribution
+          notices within Derivative Works that You distribute, alongside
+          or as an addendum to the NOTICE text from the Work, provided
+          that such additional attribution notices cannot be construed
+          as modifying the License.
+
+      You may add Your own copyright statement to Your modifications and
+      may provide additional or different license terms and conditions
+      for use, reproduction, or distribution of Your modifications, or
+      for any such Derivative Works as a whole, provided Your use,
+      reproduction, and distribution of the Work otherwise complies with
+      the conditions stated in this License.
+
+   5. Submission of Contributions. Unless You explicitly state otherwise,
+      any Contribution intentionally submitted for inclusion in the Work
+      by You to the Licensor shall be under the terms and conditions of
+      this License, without any additional terms or conditions.
+      Notwithstanding the above, nothing herein shall supersede or modify
+      the terms of any separate license agreement you may have executed
+      with Licensor regarding such Contributions.
+
+   6. Trademarks. This License does not grant permission to use the trade
+      names, trademarks, service marks, or product names of the Licensor,
+      except as required for reasonable and customary use in describing the
+      origin of the Work and reproducing the content of the NOTICE file.
+
+   7. Disclaimer of Warranty. Unless required by applicable law or
+      agreed to in writing, Licensor provides the Work (and each
+      Contributor provides its Contributions) on an "AS IS" BASIS,
+      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+      implied, including, without limitation, any warranties or conditions
+      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+      PARTICULAR PURPOSE. You are solely responsible for determining the
+      appropriateness of using or redistributing the Work and assume any
+      risks associated with Your exercise of permissions under this License.
+
+   8. Limitation of Liability. In no event and under no legal theory,
+      whether in tort (including negligence), contract, or otherwise,
+      unless required by applicable law (such as deliberate and grossly
+      negligent acts) or agreed to in writing, shall any Contributor be
+      liable to You for damages, including any direct, indirect, special,
+      incidental, or consequential damages of any character arising as a
+      result of this License or out of the use or inability to use the
+      Work (including but not limited to damages for loss of goodwill,
+      work stoppage, computer failure or malfunction, or any and all
+      other commercial damages or losses), even if such Contributor
+      has been advised of the possibility of such damages.
+
+   9. Accepting Warranty or Additional Liability. While redistributing
+      the Work or Derivative Works thereof, You may choose to offer,
+      and charge a fee for, acceptance of support, warranty, indemnity,
+      or other liability obligations and/or rights consistent with this
+      License. However, in accepting such obligations, You may act only
+      on Your own behalf and on Your sole responsibility, not on behalf
+      of any other Contributor, and only if You agree to indemnify,
+      defend, and hold each Contributor harmless for any liability
+      incurred by, or claims asserted against, such Contributor by reason
+      of your accepting any such warranty or additional liability.
+
+   END OF TERMS AND CONDITIONS
+
+   APPENDIX: How to apply the Apache License to your work.
+
+      To apply the Apache License to your work, attach the following
+      boilerplate notice, with the fields enclosed by brackets "[]"
+      replaced with your own identifying information. (Don't include
+      the brackets!)  The text should be enclosed in the appropriate
+      comment syntax for the file format. We also recommend that a
+      file or class name and description of purpose be included on the
+      same "printed page" as the copyright notice for easier
+      identification within third-party archives.
+
+   Copyright [yyyy] [name of copyright owner]
+
+   Licensed under the Apache License, Version 2.0 (the "License");
+   you may not use this file except in compliance with the License.
+   You may obtain a copy of the License at
+
+       http://www.apache.org/licenses/LICENSE-2.0
+
+   Unless required by applicable law or agreed to in writing, software
+   distributed under the License is distributed on an "AS IS" BASIS,
+   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either expressed or implied.
+   See the License for the specific language governing permissions and
+   limitations under the License.

langidentify-1.0.0/PKG-INFO

@@ -0,0 +1,210 @@
+Metadata-Version: 2.4
+Name: langidentify
+Version: 1.0.0
+Summary: Fast, high-accuracy language detection for Python. Uses ngram classification augmented with a topwords signal for improved short-text accuracy. Supports 80+ languages.
+Author-email: Jeremy Lilley <jeremy@jlilley.net>
+License-Expression: Apache-2.0
+Project-URL: Homepage, https://github.com/jlpka/langidentify
+Project-URL: Repository, https://github.com/jlpka/langidentify
+Keywords: language-detection,nlp,ngram,text-classification
+Classifier: Development Status :: 5 - Production/Stable
+Classifier: Intended Audience :: Developers
+Classifier: Programming Language :: Python :: 3
+Classifier: Topic :: Text Processing :: Linguistic
+Requires-Python: >=3.9
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: cjclassifier>=1.0.3
+Provides-Extra: full
+Requires-Dist: langidentify-full-model>=1.0.0; extra == "full"
+Provides-Extra: dev
+Requires-Dist: pytest>=7.0; extra == "dev"
+Dynamic: license-file
+
+# LangIdentify
+
+A fast, lightweight language detection library for Python. LangIdentify detects
+the language of text using a combination of ngram frequency analysis and
+whole-word ("topwords") frequency signals, both trained on the Wikipedia corpus.
+It supports 80+ languages across Latin, Cyrillic, Arabic, CJK, and many other
+scripts, and runs entirely offline with no network calls.
+
+Most language detection libraries rely solely on character ngram models. While
+ngrams are an excellent primary signal, they struggle with short or ambiguous
+text. LangIdentify augments ngram scoring with a topwords signal that identifies
+common whole words from each language, giving it higher accuracy on short
+sentences than other approaches -- even on two-word phrases.
+
+## Quick start
+
+### Install
+
+```bash
+pip install langidentify
+```
+
+For the full (higher accuracy) model:
+
+```bash
+pip install "langidentify[full]"
+```
+
+### Basic usage
+
+```python
+from langidentify import Detector, Model, Language
+
+# Load the model for the languages you care about.
+languages = Language.from_comma_separated("en,fr,de,es,it")
+model = Model.load(languages)
+
+# Create a detector (lightweight, not thread-safe -- use one per thread).
+detector = Detector(model)
+
+# Detect.
+lang = detector.detect("Bonjour le monde")
+print(lang)            # Language.FRENCH
+print(lang.iso_code)   # fr
+```
+
+### Inspecting results
+
+After detection, `detector.results` provides scoring details:
+
+```python
+detector.detect("The quick brown fox")
+results = detector.results
+print(results.result)  # Language.ENGLISH
+print(results.gap)     # confidence gap (0.0 = close, 1.0 = decisive)
+```
+
+### Incremental detection
+
+For streaming or multi-part text:
+
+```python
+detector.clear_scores()
+detector.add_text("Bonjour")
+detector.add_text(" le monde")
+result = detector.compute_result()  # Language.FRENCH
+```
+
+### Language boosts
+
+When you have prior context (e.g. an HTTP Accept-Language header), you can bias
+detection toward expected languages:
+
+```python
+boosts = model.build_boost_array({Language.FRENCH: 0.08})
+lang = detector.detect("message", boosts)  # FRENCH
+# Without the boost, "message" is ambiguous between English and French.
+```
+
+### Loading from a filesystem path
+
+If you prefer to point directly at model data files instead of using the
+bundled package data:
+
+```python
+model = Model.load_from_path("/path/to/models/lite", languages)
+```
+
+## Choosing languages
+
+**Configure only the languages you actually need.** Each additional language
+increases loading time and memory usage. Closely related languages can
+cross-detect on very short phrases -- for example, adding Luxembourgish when
+you only need German may cause short German phrases to be misidentified.
+
+Group aliases are supported for convenience:
+
+| Alias | Languages |
+|-------|-----------|
+| `efigs` | English, French, Italian, German, Spanish |
+| `efigsnp` | EFIGS + Dutch, Portuguese |
+| `europe_west_common` | EFIGSNP + Nordic languages |
+| `europe_common` | Western + Eastern European + Cyrillic |
+| `cjk` | Chinese (Simplified/Traditional), Japanese, Korean |
+| `latin_alphabet` | All Latin-script languages |
+| `unique_alphabet` | Languages where the script implies the language (e.g. Thai, Greek) |
+
+```python
+languages = Language.from_comma_separated("europe_west_common,cjk")
+```
+
+## Lite vs. full model
+
+Both models are trained from the same Wikipedia data but cropped at different
+probability floors:
+
+| | Lite | Full |
+|---|---|---|
+| Log-probability floor | -12 | -15 |
+| Disk size (all languages) | ~17 MB | ~89 MB |
+| Best for | Most use cases | Maximum accuracy when memory is not a concern |
+
+By default, `Model.load()` auto-discovers which model variant is available,
+preferring the full model. To force a variant:
+
+```python
+model = Model.load_lite(languages)   # recommended default
+model = Model.load_full(languages)   # higher accuracy, more memory
+```
+
+### Getting the full model
+
+The lite model is sufficient for most use cases. If you want the full model
+for maximum accuracy, install the companion package:
+
+```bash
+pip install "langidentify[full]"
+```
+
+This installs the `langidentify-full-model` package, which provides the full
+model data. Once installed, `Model.load()` will automatically prefer the full
+model, or you can request it explicitly:
+
+```python
+model = Model.load_full(languages)
+```
+
+## CJK detection
+
+Chinese/Japanese disambiguation is handled by the
+[cjclassifier](https://pypi.org/project/cjclassifier/) package, which is
+installed automatically as a dependency. Korean uses the distinct Hangul script
+and is identified by alphabet alone.
+
+## Thread safety
+
+`Model` caches loaded data in a module-level dict protected by a lock.
+`Detector` is lightweight to construct and intentionally **not thread-safe**.
+For concurrent detection, use a separate instance per thread:
+
+```python
+import threading
+
+model = Model.load(languages)  # shared, thread-safe
+
+local = threading.local()
+
+def get_detector():
+    if not hasattr(local, "detector"):
+        local.detector = Detector(model)
+    return local.detector
+
+# In each thread:
+lang = get_detector().detect(text)
+```
+
+## Requirements
+
+- Python 3.9+
+- [cjclassifier](https://pypi.org/project/cjclassifier/) (installed automatically)
+
+## License
+
+Apache License 2.0 -- see [LICENSE](LICENSE).
+
+The bundled models contain statistical parameters derived from Wikipedia text.
+The models do not contain or reproduce Wikipedia text.

langidentify-1.0.0/README.md

@@ -0,0 +1,187 @@
+# LangIdentify
+
+A fast, lightweight language detection library for Python. LangIdentify detects
+the language of text using a combination of ngram frequency analysis and
+whole-word ("topwords") frequency signals, both trained on the Wikipedia corpus.
+It supports 80+ languages across Latin, Cyrillic, Arabic, CJK, and many other
+scripts, and runs entirely offline with no network calls.
+
+Most language detection libraries rely solely on character ngram models. While
+ngrams are an excellent primary signal, they struggle with short or ambiguous
+text. LangIdentify augments ngram scoring with a topwords signal that identifies
+common whole words from each language, giving it higher accuracy on short
+sentences than other approaches -- even on two-word phrases.
+
+## Quick start
+
+### Install
+
+```bash
+pip install langidentify
+```
+
+For the full (higher accuracy) model:
+
+```bash
+pip install "langidentify[full]"
+```
+
+### Basic usage
+
+```python
+from langidentify import Detector, Model, Language
+
+# Load the model for the languages you care about.
+languages = Language.from_comma_separated("en,fr,de,es,it")
+model = Model.load(languages)
+
+# Create a detector (lightweight, not thread-safe -- use one per thread).
+detector = Detector(model)
+
+# Detect.
+lang = detector.detect("Bonjour le monde")
+print(lang)            # Language.FRENCH
+print(lang.iso_code)   # fr
+```
+
+### Inspecting results
+
+After detection, `detector.results` provides scoring details:
+
+```python
+detector.detect("The quick brown fox")
+results = detector.results
+print(results.result)  # Language.ENGLISH
+print(results.gap)     # confidence gap (0.0 = close, 1.0 = decisive)
+```
+
+### Incremental detection
+
+For streaming or multi-part text:
+
+```python
+detector.clear_scores()
+detector.add_text("Bonjour")
+detector.add_text(" le monde")
+result = detector.compute_result()  # Language.FRENCH
+```
+
+### Language boosts
+
+When you have prior context (e.g. an HTTP Accept-Language header), you can bias
+detection toward expected languages:
+
+```python
+boosts = model.build_boost_array({Language.FRENCH: 0.08})
+lang = detector.detect("message", boosts)  # FRENCH
+# Without the boost, "message" is ambiguous between English and French.
+```
+
+### Loading from a filesystem path
+
+If you prefer to point directly at model data files instead of using the
+bundled package data:
+
+```python
+model = Model.load_from_path("/path/to/models/lite", languages)
+```
+
+## Choosing languages
+
+**Configure only the languages you actually need.** Each additional language
+increases loading time and memory usage. Closely related languages can
+cross-detect on very short phrases -- for example, adding Luxembourgish when
+you only need German may cause short German phrases to be misidentified.
+
+Group aliases are supported for convenience:
+
+| Alias | Languages |
+|-------|-----------|
+| `efigs` | English, French, Italian, German, Spanish |
+| `efigsnp` | EFIGS + Dutch, Portuguese |
+| `europe_west_common` | EFIGSNP + Nordic languages |
+| `europe_common` | Western + Eastern European + Cyrillic |
+| `cjk` | Chinese (Simplified/Traditional), Japanese, Korean |
+| `latin_alphabet` | All Latin-script languages |
+| `unique_alphabet` | Languages where the script implies the language (e.g. Thai, Greek) |
+
+```python
+languages = Language.from_comma_separated("europe_west_common,cjk")
+```
+
+## Lite vs. full model
+
+Both models are trained from the same Wikipedia data but cropped at different
+probability floors:
+
+| | Lite | Full |
+|---|---|---|
+| Log-probability floor | -12 | -15 |
+| Disk size (all languages) | ~17 MB | ~89 MB |
+| Best for | Most use cases | Maximum accuracy when memory is not a concern |
+
+By default, `Model.load()` auto-discovers which model variant is available,
+preferring the full model. To force a variant:
+
+```python
+model = Model.load_lite(languages)   # recommended default
+model = Model.load_full(languages)   # higher accuracy, more memory
+```
+
+### Getting the full model
+
+The lite model is sufficient for most use cases. If you want the full model
+for maximum accuracy, install the companion package:
+
+```bash
+pip install "langidentify[full]"
+```
+
+This installs the `langidentify-full-model` package, which provides the full
+model data. Once installed, `Model.load()` will automatically prefer the full
+model, or you can request it explicitly:
+
+```python
+model = Model.load_full(languages)
+```
+
+## CJK detection
+
+Chinese/Japanese disambiguation is handled by the
+[cjclassifier](https://pypi.org/project/cjclassifier/) package, which is
+installed automatically as a dependency. Korean uses the distinct Hangul script
+and is identified by alphabet alone.
+
+## Thread safety
+
+`Model` caches loaded data in a module-level dict protected by a lock.
+`Detector` is lightweight to construct and intentionally **not thread-safe**.
+For concurrent detection, use a separate instance per thread:
+
+```python
+import threading
+
+model = Model.load(languages)  # shared, thread-safe
+
+local = threading.local()
+
+def get_detector():
+    if not hasattr(local, "detector"):
+        local.detector = Detector(model)
+    return local.detector
+
+# In each thread:
+lang = get_detector().detect(text)
+```
+
+## Requirements
+
+- Python 3.9+
+- [cjclassifier](https://pypi.org/project/cjclassifier/) (installed automatically)
+
+## License
+
+Apache License 2.0 -- see [LICENSE](LICENSE).
+
+The bundled models contain statistical parameters derived from Wikipedia text.
+The models do not contain or reproduce Wikipedia text.

langidentify-1.0.0/pyproject.toml

@@ -0,0 +1,44 @@
+[build-system]
+requires = ["setuptools>=68.0", "wheel"]
+build-backend = "setuptools.build_meta"
+
+[project]
+name = "langidentify"
+version = "1.0.0"
+description = "Fast, high-accuracy language detection for Python. Uses ngram classification augmented with a topwords signal for improved short-text accuracy. Supports 80+ languages."
+readme = "README.md"
+license = "Apache-2.0"
+license-files = ["LICENSE"]
+requires-python = ">=3.9"
+authors = [
+    {name = "Jeremy Lilley", email = "jeremy@jlilley.net"},
+]
+keywords = ["language-detection", "nlp", "ngram", "text-classification"]
+classifiers = [
+    "Development Status :: 5 - Production/Stable",
+    "Intended Audience :: Developers",
+    "Programming Language :: Python :: 3",
+    "Topic :: Text Processing :: Linguistic",
+]
+dependencies = [
+    "cjclassifier>=1.0.3",
+]
+
+[project.optional-dependencies]
+full = [
+    "langidentify-full-model>=1.0.0",
+]
+dev = [
+    "pytest>=7.0",
+]
+
+[project.urls]
+Homepage = "https://github.com/jlpka/langidentify"
+Repository = "https://github.com/jlpka/langidentify"
+
+[tool.setuptools.packages.find]
+where = ["src"]
+
+[tool.setuptools.package-data]
+"langidentify.models.lite" = ["*.txt.gz", "*.txt"]
+"langidentify.models.full" = ["*.txt.gz", "*.txt"]

langidentify-1.0.0/setup.cfg

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

langidentify-1.0.0/src/langidentify/__init__.py

@@ -0,0 +1,44 @@
+# Copyright 2026 Jeremy Lilley (jeremy@jlilley.net)
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+"""langidentify — fast language detection using n-gram and topword scoring.
+
+Usage::
+
+    from langidentify import Detector, Model, Language
+
+    languages = Language.from_comma_separated("en,fr,de")
+    model = Model.load(languages)
+    detector = Detector(model)
+    lang = detector.detect("Bonjour le monde")
+    print(lang)  # Language.FRENCH
+"""
+
+from langidentify.alphabet import Alphabet
+from langidentify.accent_remover import AccentRemover
+from langidentify.detector import Detector, Results, Scores
+from langidentify.language import Language
+from langidentify.model import Model
+
+__all__ = [
+    "Alphabet",
+    "AccentRemover",
+    "Detector",
+    "Language",
+    "Model",
+    "Results",
+    "Scores",
+]
+
+__version__ = "1.0.0"