hfst-altlab 0.0.1.dev0__tar.gz

hfst_altlab-0.0.1.dev0/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 express or implied.
+   See the License for the specific language governing permissions and
+   limitations under the License.

hfst_altlab-0.0.1.dev0/PKG-INFO

@@ -0,0 +1,36 @@
+Metadata-Version: 2.4
+Name: hfst-altlab
+Version: 0.0.1.dev0
+Summary: A python wrapper for accessing Helsinki Finite State Transducers used at ALTLab
+Author-email: Felipe Bañados Schwerter <banadoss@ualberta.ca>
+License-Expression: Apache-2.0
+Project-URL: Homepage, https://github.com/UAlbertaALTLab/hfst-altlab
+Project-URL: Issues, https://github.com/UAlbertaALTLab/hfst-altlab/issues
+Classifier: Topic :: Text Processing :: Linguistic
+Classifier: Topic :: Software Development :: Build Tools
+Requires-Python: >=3.9
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Dynamic: license-file
+
+hfst-altlab
+===========
+
+A wrapper on the [hfst][] python package, currently working as a replacement for [hfst-optimized-lookup][], built for [itwêwina][].
+
+[itwêwina]: https://itwewina.altlab.app
+[hfst-optimized-lookup]: https://github.com/UAlbertaALTLab/hfst-optimized-lookup
+[hfst]: https://pypi.org/project/hfst/
+
+Languages currently supported:
+  - [python](python)
+
+[hfst] is a great toolkit with all sorts of functionality, and is
+indispensable for building FSTs, but for various applications that only
+want to do unweighted hfstol lookups, this package may be easier to use.
+
+[hfst]: https://github.com/hfst/hfst
+
+Although eventually we want to restore maintenance of the [hfst-optimized-lookup][] package, as it follows a more lightweight approach, we are in the process of contacting the maintainers of the pypi package to take over.  In the meantime, we want to use this project as an upstream-synced implementation and as a way to explore more advanced behaviours that can be useful for many language projects (especially for [morphodict][]). In particular, we wanted to extend the API to account for weighted FSTs and we intend to explore making flag diacritics available in the not-so-distant future.
+
+[morphodict]: https://github.com/UAlbertaALTLab/morphodict

hfst_altlab-0.0.1.dev0/README.md

@@ -0,0 +1,21 @@
+hfst-altlab
+===========
+
+A wrapper on the [hfst][] python package, currently working as a replacement for [hfst-optimized-lookup][], built for [itwêwina][].
+
+[itwêwina]: https://itwewina.altlab.app
+[hfst-optimized-lookup]: https://github.com/UAlbertaALTLab/hfst-optimized-lookup
+[hfst]: https://pypi.org/project/hfst/
+
+Languages currently supported:
+  - [python](python)
+
+[hfst] is a great toolkit with all sorts of functionality, and is
+indispensable for building FSTs, but for various applications that only
+want to do unweighted hfstol lookups, this package may be easier to use.
+
+[hfst]: https://github.com/hfst/hfst
+
+Although eventually we want to restore maintenance of the [hfst-optimized-lookup][] package, as it follows a more lightweight approach, we are in the process of contacting the maintainers of the pypi package to take over.  In the meantime, we want to use this project as an upstream-synced implementation and as a way to explore more advanced behaviours that can be useful for many language projects (especially for [morphodict][]). In particular, we wanted to extend the API to account for weighted FSTs and we intend to explore making flag diacritics available in the not-so-distant future.
+
+[morphodict]: https://github.com/UAlbertaALTLab/morphodict

hfst_altlab-0.0.1.dev0/pyproject.toml

@@ -0,0 +1,23 @@
+[build-system]
+requires = ["setuptools"]
+build-backend = "setuptools.build_meta"
+
+[project]
+name = "hfst-altlab"
+version = "0.0.1.dev0"
+authors = [
+    { name="Felipe Bañados Schwerter", email="banadoss@ualberta.ca" },
+]
+description = "A python wrapper for accessing Helsinki Finite State Transducers used at ALTLab"
+readme = "README.md"
+requires-python = ">=3.9"
+classifiers = [
+    "Topic :: Text Processing :: Linguistic",
+    "Topic :: Software Development :: Build Tools"
+]
+license = "Apache-2.0"
+license-files = ["LICENSE"]
+
+[project.urls]
+Homepage = "https://github.com/UAlbertaALTLab/hfst-altlab"
+Issues = "https://github.com/UAlbertaALTLab/hfst-altlab/issues"

hfst_altlab-0.0.1.dev0/setup.cfg

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

hfst_altlab-0.0.1.dev0/src/__init__.py

@@ -0,0 +1,191 @@
+import hfst
+from pathlib import Path
+from errno import ENOENT
+from os import strerror
+from .types import Analysis
+
+
+class TransducerFile:
+    """
+    Loads an ``.hfst`` or an ``.hfstol`` transducer file.
+    This is intended as a replacement and extension of the
+    hfst-optimized-lookup python package, but depending on the
+    hfst project to pack the C code directly.  This provides the
+    added benefit of regaining access to weighted FSTs without extra work.
+    Note that lookup will only be fast if the input file has been processed
+    into the hfstol format.
+    """
+
+    def __init__(self, filename: Path | str, search_cutoff: int = 60):
+        self.cutoff = search_cutoff
+
+        if not Path(filename).exists():
+            exn = FileNotFoundError(f"Transducer not found: ‘{str(filename)}’")
+            raise exn
+
+        # Now we extract the transducer and store it.
+        try:
+            stream = hfst.HfstInputStream(str(filename))
+        except hfst.exceptions.NotTransducerStreamException as e:
+            # Expected message for backwards compatibility.
+            e.args = ("wrong or corrupt file?",)
+            raise e
+
+        transducers = stream.read_all()
+        if not len(transducers) == 1:
+            error = ValueError(self)
+            error.add_note("We expected a single transducer to arise in the file.")
+            stream.close()
+            raise error
+
+        stream.close()
+        self.transducer = transducers[0]
+        if self.transducer.is_infinitely_ambiguous():
+            raise RuntimeWarning("The transducer is infinitely ambiguous.")
+        if not (
+            self.transducer.get_type()
+            in [
+                hfst.ImplementationType.HFST_OL_TYPE,
+                hfst.ImplementationType.HFST_OLW_TYPE,
+            ]
+        ):
+            print("Transducer not optimized.  Optimizing...")
+            self.transducer.lookup_optimize()
+            print("Done.")
+
+    def bulk_lookup(self, words: list[str]) -> dict[str, set[str]]:
+        """
+         Like ``lookup()`` but applied to multiple inputs. Useful for generating multiple
+        surface forms.
+
+        :param words: list of words to lookup
+        :type words: list[str]
+        :return: a dictionary mapping words in the input to a set of its tranductions
+        :rtype: dict[str, set[str]]
+        """
+        return {word: set(self.lookup(word)) for word in words}
+
+    def lookup(self, input: str) -> list[str]:
+        """
+        Lookup the input string, returning a list of tranductions.  This is
+        most similar to using ``hfst-optimized-lookup`` on the command line.
+
+        :param str string: The string to lookup.
+        :return: list of analyses as concatenated strings, or an empty list if the input
+            cannot be analyzed.
+        :rtype: list[str]
+        """
+        return ["".join(transduction) for transduction in self.lookup_symbols(input)]
+
+    def weighted_lookup_lemma_with_affixes(
+        self, surface_form: str
+    ) -> list[tuple[float, Analysis]]:
+        """
+        Analyze the input string, returning a list
+        of tuples containing a ``float`` and a :py:class:`types.Analysis` object.
+
+        .. note::
+            this method assumes an analyzer in which all multicharacter symbols
+            represent affixes, and all lexical symbols are contiguous.
+
+
+        :param str string: The string to lookup.
+        :return: list of analyses as :py:class:`types.Analysis`
+            objects, or an empty list if there are no analyses.
+        :rtype: list of :py:class:`types.Analysis`
+        """
+        raw_weighted_analyses = self.weighted_lookup_symbols(surface_form)
+        return [
+            (weight, _parse_analysis(analysis))
+            for weight, analysis in raw_weighted_analyses
+        ]
+
+    def lookup_lemma_with_affixes(self, surface_form: str) -> list[Analysis]:
+        return [
+            analysis
+            for weight, analysis in self.weighted_lookup_lemma_with_affixes(
+                surface_form
+            )
+        ]
+
+    def lookup_symbols(self, input: str) -> list[list[str]]:
+        """
+        Transduce the input string. The result is a list of tranductions. Each
+        tranduction is a list of symbols returned in the model; that is, the symbols are
+        not concatenated into a single string.
+
+        :param str input: The string to lookup.
+        :return:
+        :rtype: list[list[str]]
+        """
+        return [
+            transduction for weight, transduction in self.weighted_lookup_symbols(input)
+        ]
+
+    def weighted_lookup_symbols(self, input: str) -> list[tuple[float, list[str]]]:
+        """
+        Transduce the input string. The result is a list of weighted tranductions. Each
+        weighted tranduction is a tuple with a float for the weight and a list of symbols returned in the model; that is, the symbols are
+        not concatenated into a single string.
+
+        :param str input: The string to lookup.
+        :return:
+        :rtype: list[tuple[float,list[str]]]
+        """
+        return [
+            (
+                float(weight),
+                [
+                    symbol
+                    for symbol in symbols
+                    if not hfst.is_diacritic(symbol) and symbol
+                ],
+            )
+            for weight, symbols in self.weighted_lookup_symbols_with_flags(input)
+        ]
+
+    def weighted_lookup_symbols_with_flags(
+        self, input: str
+    ) -> list[tuple[float, list[str]]]:
+        """
+        Transduce the input string, preserving the weight information coming from HFST and separating each symbol
+
+        :param str input: The string to lookup.
+        :return: A list of tuples, each containing the weight(float), and a list of strings, each a language symbol
+        :rtype: list[tuple[float,list[str]]]
+        """
+        return list(
+            self.transducer.lookup(input, time_cutoff=self.cutoff, output="raw")
+        )
+
+    def symbol_count(self) -> int:
+        """
+        symbol_count() -> int
+
+        Returns the number of symbols in the sigma (the symbol table or alphabet).
+
+        :rtype: int
+        """
+        return len(self.transducer.get_alphabet())
+
+
+def _parse_analysis(letters_and_tags: list[str]) -> Analysis:
+    prefix_tags: list[str] = []
+    lemma_chars: list[str] = []
+    suffix_tags: list[str] = []
+
+    tag_destination = prefix_tags
+    for symbol in letters_and_tags:
+        if not hfst.is_diacritic(symbol):
+            if len(symbol) == 1:
+                lemma_chars.append(symbol)
+                tag_destination = suffix_tags
+            else:
+                assert len(symbol) > 1
+                tag_destination.append(symbol)
+
+    return Analysis(
+        tuple(prefix_tags),
+        "".join(lemma_chars),
+        tuple(suffix_tags),
+    )

hfst_altlab-0.0.1.dev0/src/hfst_altlab.egg-info/PKG-INFO

@@ -0,0 +1,36 @@
+Metadata-Version: 2.4
+Name: hfst-altlab
+Version: 0.0.1.dev0
+Summary: A python wrapper for accessing Helsinki Finite State Transducers used at ALTLab
+Author-email: Felipe Bañados Schwerter <banadoss@ualberta.ca>
+License-Expression: Apache-2.0
+Project-URL: Homepage, https://github.com/UAlbertaALTLab/hfst-altlab
+Project-URL: Issues, https://github.com/UAlbertaALTLab/hfst-altlab/issues
+Classifier: Topic :: Text Processing :: Linguistic
+Classifier: Topic :: Software Development :: Build Tools
+Requires-Python: >=3.9
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Dynamic: license-file
+
+hfst-altlab
+===========
+
+A wrapper on the [hfst][] python package, currently working as a replacement for [hfst-optimized-lookup][], built for [itwêwina][].
+
+[itwêwina]: https://itwewina.altlab.app
+[hfst-optimized-lookup]: https://github.com/UAlbertaALTLab/hfst-optimized-lookup
+[hfst]: https://pypi.org/project/hfst/
+
+Languages currently supported:
+  - [python](python)
+
+[hfst] is a great toolkit with all sorts of functionality, and is
+indispensable for building FSTs, but for various applications that only
+want to do unweighted hfstol lookups, this package may be easier to use.
+
+[hfst]: https://github.com/hfst/hfst
+
+Although eventually we want to restore maintenance of the [hfst-optimized-lookup][] package, as it follows a more lightweight approach, we are in the process of contacting the maintainers of the pypi package to take over.  In the meantime, we want to use this project as an upstream-synced implementation and as a way to explore more advanced behaviours that can be useful for many language projects (especially for [morphodict][]). In particular, we wanted to extend the API to account for weighted FSTs and we intend to explore making flag diacritics available in the not-so-distant future.
+
+[morphodict]: https://github.com/UAlbertaALTLab/morphodict

hfst_altlab-0.0.1.dev0/src/hfst_altlab.egg-info/SOURCES.txt

@@ -0,0 +1,10 @@
+LICENSE
+README.md
+pyproject.toml
+src/__init__.py
+src/import_test.py
+src/types.py
+src/hfst_altlab.egg-info/PKG-INFO
+src/hfst_altlab.egg-info/SOURCES.txt
+src/hfst_altlab.egg-info/dependency_links.txt
+src/hfst_altlab.egg-info/top_level.txt

hfst_altlab-0.0.1.dev0/src/hfst_altlab.egg-info/dependency_links.txt

@@ -0,0 +1 @@
+

hfst_altlab-0.0.1.dev0/src/hfst_altlab.egg-info/top_level.txt

@@ -0,0 +1,3 @@
+__init__
+import_test
+types

hfst_altlab-0.0.1.dev0/src/import_test.py

@@ -0,0 +1,192 @@
+"""
+This file has been imported from https://github.com/UAlbertaALTLab/hfst-optimized-lookup/,
+to act as a compatibility check layer.  Further tests should be incorporated somewhere else.
+"""
+
+from pathlib import Path
+import pytest
+
+from . import TransducerFile, Analysis
+
+
+@pytest.fixture(scope="session")
+def project_root_path(request):
+    return request.config.rootpath
+
+
+TEST_FST = "crk-relaxed-analyzer-for-dictionary.hfstol"
+
+
+# scope="session" reuses the FST for all tests that use this fixture
+@pytest.fixture(scope="session")
+def fst(project_root_path) -> TransducerFile:
+    return TransducerFile(project_root_path / TEST_FST)
+
+
+def test_symbol_count(fst: TransducerFile) -> None:
+    # If this returned a non-number, we’d get a TypeError here.
+    assert fst.symbol_count() > 0
+
+
+def test_subsequent_lookups(fst: TransducerFile) -> None:
+    assert fst.lookup("itwêwina") == ["itwêwin+N+I+Pl"]
+    assert fst.lookup("nikî-nipân") == ["PV/ki+nipâw+V+AI+Ind+1Sg"]
+
+
+def test_valid_lookup_with_invalid_symbol(fst: TransducerFile) -> None:
+    assert fst.lookup("avocado") == []
+    assert fst.lookup("navajo") == []
+
+
+def test_multiple_analyses(fst: TransducerFile) -> None:
+    assert fst.lookup("môswa") == ["môswa+N+A+Sg", "môswa+N+A+Obv"]
+
+
+EXPECTED_BULK_LOOKUP_RESULT_1 = {
+    "itwêwina": set(["itwêwin+N+I+Pl"]),
+    "nikî-nipân": set(["PV/ki+nipâw+V+AI+Ind+1Sg"]),
+    "môswa": set(["môswa+N+A+Sg", "môswa+N+A+Obv"]),
+}
+
+
+def test_bulk_lookup(fst: TransducerFile) -> None:
+    assert (
+        fst.bulk_lookup(list(EXPECTED_BULK_LOOKUP_RESULT_1.keys()))
+        == EXPECTED_BULK_LOOKUP_RESULT_1
+    )
+
+
+def test_bulk_lookup_with_iterator(fst: TransducerFile) -> None:
+    assert (
+        fst.bulk_lookup([w for w in EXPECTED_BULK_LOOKUP_RESULT_1.keys()])
+        == EXPECTED_BULK_LOOKUP_RESULT_1
+    )
+
+
+def test_create_from_path_obj(project_root_path) -> None:
+    fst = TransducerFile(Path(project_root_path / TEST_FST))
+    assert fst.lookup("itwêwina") == ["itwêwin+N+I+Pl"]
+
+
+@pytest.mark.skip("not yet implemented")
+def test_limit(fst: TransducerFile) -> None:
+    assert fst.lookup("môswa", limit=1) == ["môswa+N+A+Sg"]  # type: ignore
+
+
+@pytest.mark.parametrize(
+    ("surface", "deep"),
+    [
+        [
+            "môswa",
+            [
+                ["m", "ô", "s", "w", "a", "+N", "+A", "+Sg"],
+                ["m", "ô", "s", "w", "a", "+N", "+A", "+Obv"],
+            ],
+        ],
+        [
+            "nikî-nipân",
+            [["PV/ki+", "n", "i", "p", "â", "w", "+V", "+AI", "+Ind", "+1Sg"]],
+        ],
+    ],
+)
+def test_symbol_lookup1(
+    fst: TransducerFile, surface: str, deep: list[list[str]]
+) -> None:
+    assert fst.lookup_symbols(surface) == deep
+
+
+@pytest.mark.parametrize(
+    ("surface", "example"),
+    [
+        # VTA with a prefix:
+        (
+            "ê-mowât",
+            Analysis(("PV/e+",), "mowêw", ("+V", "+TA", "+Cnj", "+3Sg", "+4Sg/PlO")),
+        ),
+        # VAI with prefixes:
+        (
+            "ê-kî-nitawi-kâh-kîmôci-kotiskâwêyâhk",
+            Analysis(
+                prefixes=("PV/e+", "PV/ki+", "PV/nitawi+", "RdplS+", "PV/kimoci+"),
+                lemma="kotiskâwêw",
+                suffixes=("+V", "+AI", "+Cnj", "+12Pl"),
+            ),
+        ),
+        # Ipc:
+        (
+            # NOTE: assuming relaxed analyzer for dictionary which:
+            #  - understands "tansi" is a spelling of "tânisi"
+            #  - does NOT output an +Err/Orth tag!
+            "tansi",
+            Analysis((), "tânisi", ("+Ipc",)),
+        ),
+        # NA, with possession
+        (
+            "nitêm",
+            Analysis((), "atim", ("+N", "+A", "+Px1Sg", "+Sg")),
+        ),
+        # NID
+        (
+            "otâsa",
+            Analysis(
+                (),
+                "mitâs",
+                (
+                    "+N",
+                    "+I",
+                    "+D",
+                    "+Px3Sg",
+                    "+Pl",
+                ),
+            ),
+        ),
+        # VAI, no prefixes, unspecified actor:
+        (
+            "nîminâniwan",
+            Analysis((), "nîmiw", ("+V", "+AI", "+Ind", "+X")),
+        ),
+        # VII, tense prefix
+        (
+            "kî-kinêpikoskâw",
+            Analysis(
+                prefixes=("PV/ki+",),
+                lemma="kinêpikoskâw",
+                suffixes=(
+                    "+V",
+                    "+II",
+                    "+Ind",
+                    "+3Sg",
+                ),
+            ),
+        ),
+    ],
+)
+def test_lookup_lemma_with_affixes(
+    fst: TransducerFile, surface: str, example: Analysis
+) -> None:
+    analyses = fst.lookup_lemma_with_affixes(surface)
+    assert example in analyses
+
+
+def test_raises_exception_on_missing_file() -> None:
+    with pytest.raises(Exception) as exception_info:
+        TransducerFile("/does-not-exist.hfstol")
+
+    exception_messages = " ".join([str(s) for s in exception_info.value.args])
+    assert "Transducer not found" in exception_messages
+    assert "‘/does-not-exist.hfstol’" in exception_messages
+
+
+def test_raises_exception_on_invalid_file() -> None:
+    with pytest.raises(Exception) as exception_info:
+        # The python test file is not a valid transducer.
+        TransducerFile(__file__)
+
+    exception_messages = " ".join(exception_info.value.args)
+    assert "wrong or corrupt file?" in exception_messages
+
+
+if __name__ == "__main__":
+    import sys
+
+    pytest.main(sys.argv)

hfst_altlab-0.0.1.dev0/src/types.py

@@ -0,0 +1,152 @@
+from typing import NamedTuple, Tuple
+
+
+class Analysis(NamedTuple):
+    """
+    An analysis of a wordform.
+
+    This is a *named tuple*, so you can use it both with attributes and indices:
+
+    >>> analysis = Analysis(('PV/e+',), 'wâpamêw', ('+V', '+TA', '+Cnj', '+3Sg', '+4Sg/PlO'))
+
+    Using attributes:
+
+    >>> analysis.lemma
+    'wâpamêw'
+    >>> analysis.prefixes
+    ('PV/e+',)
+    >>> analysis.suffixes
+    ('+V', '+TA', '+Cnj', '+3Sg', '+4Sg/PlO')
+
+    Using with indices:
+
+    >>> len(analysis)
+    3
+    >>> analysis[0]
+    ('PV/e+',)
+    >>> analysis[1]
+    'wâpamêw'
+    >>> analysis[2]
+    ('+V', '+TA', '+Cnj', '+3Sg', '+4Sg/PlO')
+    >>> prefixes, lemma, suffix = analysis
+    >>> lemma
+    'wâpamêw'
+    """
+
+    prefixes: Tuple[str, ...]
+    """
+    Tags that appear before the lemma.
+    """
+
+    lemma: str
+    """
+    The base form of the analyzed wordform.
+    """
+
+    suffixes: Tuple[str, ...]
+    """
+    Tags that appear after the lemma.
+    """
+
+
+class RichAnalysis:
+    """The one true FST analysis class.
+
+    Put all your methods for dealing with things like `PV/e+nipâw+V+AI+Cnj+3Pl`
+    here.
+    """
+
+    def __init__(self, analysis):
+        if isinstance(analysis, Analysis):
+            self._tuple = analysis
+        elif (isinstance(analysis, list) or isinstance(analysis, tuple)) and (
+            len(analysis) == 6 or len(analysis == 3)
+        ):
+            if len(analysis == 3):
+                prefix_tags, lemma, suffix_tags = analysis
+                self._tuple = Analysis(
+                    prefixes=tuple(prefix_tags),
+                    lemma=lemma,
+                    suffixes=tuple(suffix_tags),
+                    prefix_flags=[],
+                    lemma_flags=[],
+                    suffix_flags=[],
+                )
+            else:
+                (
+                    prefix_tags,
+                    lemma,
+                    suffix_tags,
+                    prefix_flags,
+                    lemma_flags,
+                    suffix_flags,
+                ) = analysis
+                self._tuple = Analysis(
+                    prefixes=tuple(prefix_tags),
+                    lemma=lemma,
+                    suffixes=tuple(suffix_tags),
+                    prefix_flags=prefix_flags,
+                    lemma_flags=lemma_flags,
+                    suffix_flags=suffix_flags,
+                )
+        else:
+            raise Exception(f"Unsupported argument: {analysis=!r}")
+
+    @property
+    def tuple(self):
+        return self._tuple
+
+    @property
+    def lemma(self):
+        return self._tuple.lemma
+
+    @property
+    def prefix_tags(self):
+        return self._tuple.prefixes
+
+    @property
+    def suffix_tags(self):
+        return self._tuple.suffixes
+
+    def generate(self):
+        return strict_generator().lookup(self.smushed())
+
+    def generate_with_morphemes(self, inflection):
+        try:
+            results = strict_generator_with_morpheme_boundaries().lookup(self.smushed())
+            if len(results) != 1:
+                for result in results:
+                    if "".join(re.split(r"[<>]", result)) == inflection:
+                        return re.split(r"[<>]", result)
+                return None
+            return re.split(r"[<>]", results[0])
+        except RuntimeError as e:
+            print("Could not generate morphemes:", e)
+            return []
+
+    def smushed(self):
+        return "".join(self.prefix_tags) + self.lemma + "".join(self.suffix_tags)
+
+    def tag_set(self):
+        return set(self.suffix_tags + self.prefix_tags)
+
+    def tag_intersection_count(self, other):
+        """How many tags does this analysis have in common with another?"""
+        if not isinstance(other, RichAnalysis):
+            raise Exception(f"Unsupported argument: {other=!r}")
+        return len(self.tag_set().intersection(other.tag_set()))
+
+    def __iter__(self):
+        """Allows doing `head, _, tail = rich_analysis`"""
+        return iter(self._tuple)
+
+    def __hash__(self):
+        return hash(self._tuple)
+
+    def __eq__(self, other):
+        if not isinstance(other, RichAnalysis):
+            return NotImplemented
+        return self._tuple == other.tuple
+
+    def __repr__(self):
+        return f"RichAnalysis({[self.prefix_tags, self.lemma, self.suffix_tags]!r})"