hfst-altlab 0.1.2__py3-none-any.whl

hfst_altlab/__init__.py

@@ -0,0 +1,327 @@
+import hfst
+import gzip
+from pathlib import Path
+from .types import Analysis, FullAnalysis, Wordform, as_fst_input, fst_output_format
+from typing import cast, Optional
+from collections.abc import Callable
+
+
+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.
+
+    :param filename: The path of the transducer
+    :param search_cutoff: The maximum amount of time (in seconds) that the search will go on for.  The intention of a limit is to avoid search getting stuck.  Defaults to a minute.
+    """
+
+    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:
+            # Workaround for FOMABIN formats
+            with open(filename, "rb") as f:
+                if f.read(3) == b"\x1f\x8b\x08":
+                    # It is a gzipped file!
+                    print(
+                        "\n".join(
+                            [
+                                f"The Transducer file {filename} is compressed.",
+                                "Unfortunately, our library cannot currently handle directly compressed files (e.g. .fomabin).",
+                                "Please decompress the file first.",
+                                "If you don't know how, you can use the hfst_altlab.decompress_foma function as follows:\n\n",
+                                "from hfst_altlab import decompress_foma",
+                                'with open(output_name, "wb") as f:',
+                                f'  with decompress_foma("{str(filename)}") as fst:',
+                                f"    f.write(fst.read())\n\n",
+                            ]
+                        )
+                    )
+                    raise ValueError(filename)
+                else:
+                    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():
+            print(f"Warning: The transducer at {filename} 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.convert(hfst.ImplementationType.HFST_OLW_TYPE)
+            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.
+
+        .. note:: Backwards-compatible with ``hfst-optimized-lookup``
+
+        :param words: list of words to lookup
+        :return: a dictionary mapping words in the input to a set of its tranductions
+        """
+        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.
+
+        .. note:: Backwards-compatible with ``hfst-optimized-lookup``
+
+        :param input: The string to lookup.
+        :return: list of analyses as concatenated strings, or an empty list if the input
+            cannot be analyzed.
+        """
+        return ["".join(transduction) for transduction in self.lookup_symbols(input)]
+
+    def lookup_lemma_with_affixes(self, surface_form: str) -> list[Analysis]:
+        """
+        Like lookup, but separates the results into a tuple of prefixes, a lemma, and a tuple of suffixes.  Expected to be used only on analyser FSTs.
+
+        .. note:: Backwards-compatible with ``hfst-optimized-lookup``
+
+        :param surface_form: The entry to search for.
+        """
+        return [
+            analysis.analysis
+            for analysis in self.weighted_lookup_full_analysis(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.
+
+        .. note:: Backwards-compatible with ``hfst-optimized-lookup``
+
+        :param input: The string to lookup.
+        """
+        return [
+            [x for x in analysis.tokens if x and not hfst.is_diacritic(x)]
+            for analysis in self.weighted_lookup_full_analysis(input)
+        ]
+
+    def _weighted_lookup(self, input: str) -> list[tuple[str, tuple[str, ...]]]:
+        """
+        Internal Function. Transduce the input string. The result is a list of weighted tranductions. Each
+        weighted tranduction is a tuple with a number for the weight and a list of symbols returned in the model; that is, the symbols are
+        not concatenated into a single string.
+
+        :param input: The string to lookup.
+        :return:
+        """
+        return cast(
+            list[tuple[str, tuple[str, ...]]],
+            self.transducer.lookup(str(input), time_cutoff=self.cutoff, output="raw"),
+        )
+
+    def weighted_lookup_full_analysis(
+        self, wordform: str | Wordform, generator: Optional["TransducerFile"] = None
+    ) -> list[FullAnalysis]:
+        """
+        Transduce a wordform into a list of analyzed outputs.  This method is likely only useful for analyser FSTs.
+
+        If a generator is provided, it will incorporate a standardized version of the string when available.
+        That is, it will pass the output to a secondary FST, and check if all the outputs of that "generator" FST match for an output.
+        If so, the output will be marked with the output string in the `standardized` field (See :py:class:`hfst_altlab.FullAnalysis`)
+
+        :param wordform: The string to lookup.
+        :param generator: The FST that will be used to fill the standardized version of the wordform from the produced analysis.
+        """
+        if generator:
+
+            def generate(tokens: tuple[str, ...]) -> str | None:
+                entry: str | None = None
+                for _, output in generator._weighted_lookup(fst_output_format(tokens)):
+                    candidate = "".join(x for x in output if x and not hfst.is_diacritic(x))
+                    if entry and entry != candidate:
+                        return None
+                    else:
+                        entry = candidate
+                return entry
+
+        else:
+
+            def generate(tokens: tuple[str, ...]) -> str | None:
+                return None
+
+        return [
+            FullAnalysis(float(weight), tokens, generate(tokens))
+            for weight, tokens in self._weighted_lookup(as_fst_input(wordform))
+        ]
+
+    def weighted_lookup_full_wordform(
+        self, analysis: str | FullAnalysis
+    ) -> list[Wordform]:
+        """
+        Transduce the input string. The result is a list of weighted wordforms. This method is likely only useful for generator FSTs.
+
+        :param analysis: The string to lookup.
+        :return:
+        """
+        return [
+            Wordform(float(weight), tokens)
+            for weight, tokens in self._weighted_lookup(as_fst_input(analysis))
+        ]
+
+    def symbol_count(self) -> int:
+        """
+        Returns the number of symbols in the sigma (the symbol table or alphabet).
+
+        .. note:: Backwards-compatible with ``hfst-optimized-lookup``
+
+        """
+        return len(self.transducer.get_alphabet())
+
+    def invert(self) -> None:
+        """
+        Invert the transducer.  That is, take what previously were outputs as inputs and produce as output what previously were inputs.
+
+        Although the same process can be done directly on the terminal, the intention of this method is to provide an easy way of obtaining the inverse FST.
+
+        .. warning:: Because the ``hfst`` python package cannot currently invert HFSTOL FSTs, we first convert the transducer to an SFST formatted equivalent.  If for any reason you find out that the inverted FST is providing unexpected results, report a bug.
+        """
+        # Unfortunately, hfst does not directly invert hfstol FSTs.
+        # We take a detour by changing to a different format.
+        # We do not use foma here just in case we are not dealing with a system that has foma.
+        self.transducer.convert(hfst.ImplementationType.SFST_TYPE)
+        self.transducer.invert()
+        self.transducer.lookup_optimize()
+        return None
+
+
+class TransducerPair:
+    """
+    This class provides a useful wrapper to combine an analyser FST and a generator FST for the same language.
+    It also provides sorted search when a distance function between two strings is provided.
+
+    For the cases when only a single FST is available but sorting is desired, use the :py:meth:`hfst_altlab.TransducerPair.duplicate` factory method, which produces a TransducerPair from a single FST.
+
+    On initialization, this class generates two :py:class:`hfst_altlab.TransducerFile` objects.
+
+    :param analyser: The path to the analyser FST (input: wordform, output: analyses)
+    :param generator: The path to the generator FST (input:analysis, output: wordforms)
+    :param search_cutoff: The maximum amount of time allowed for lookup on each transducer.
+    :param default_distance: An optional function providing a distance between two strings. (see :py:meth:`hfst_altlab.TransducerPair.analyse`)
+    """
+
+    analyser: TransducerFile
+    generator: TransducerFile
+    default_distance: None | Callable[[str, str], float]
+
+    def __init__(
+        self,
+        analyser: Path | str,
+        generator: Path | str,
+        search_cutoff: int = 60,
+        default_distance: None | Callable[[str, str], float] = None,
+    ):
+        self.analyser = TransducerFile(analyser, search_cutoff)
+        self.generator = TransducerFile(generator, search_cutoff)
+        self.default_distance = default_distance
+
+    def analyse(
+        self, input: Wordform | str, distance: None | Callable[[str, str], float] = None
+    ) -> list[FullAnalysis]:
+        """
+        Provide a list of analysis for a particular wordform using the analyser FST of this object.
+
+        If a `distance` function is provided (or the object has a `default_distance` property),
+        the results provided by the FST are sorted using the function to compute a distance between the
+        input wordform and the standardized wordform associated with each analysis (the result of applying the generator FST, if unique)
+
+        :param input: The wordform to analyse.
+        :param distance: The sorting function for this particular method call.  When it is not `None`, it overrides `default_distance`, but only for this particular call.
+        """
+        candidate = self.analyser.weighted_lookup_full_analysis(input, self.generator)
+        sort_function = distance or self.default_distance
+        if sort_function:
+            # If there is a distance function, use that for sorting
+            source = str(input)
+
+            def key(other: FullAnalysis) -> float:
+                if other.standardized is None:
+                    return float("+Infinity")
+                return sort_function(source, other.standardized)
+
+            candidate.sort(key=key)
+        return candidate
+
+    def generate(self, analysis: FullAnalysis | Analysis | str) -> list[Wordform]:
+        """
+        Provide a list of wordforms for a particular analysis using the generator FST of this object.
+
+        :param analysis: The analysis to generate via the FST.
+        """
+        input = (
+            "".join(analysis.prefixes) + analysis.lemma + "".join(analysis.suffixes)
+            if isinstance(analysis, Analysis)
+            else analysis
+        )
+        return self.generator.weighted_lookup_full_wordform(input)
+
+    @classmethod
+    def duplicate(
+        cls,
+        transducer: Path | str,
+        is_analyser: bool = False,
+        search_cutoff: int = 60,
+        default_distance: None | Callable[[str, str], float] = None,
+    ):
+        """
+        Factory Method.  Generates a TransducerPair from a single FST.  You can use the is_analyser argument to tell the direction of the input FST.  Note that the FST will be generated twice before inverting one.
+
+        :param transducer: The location of the single FST used to generate a :py:class:`hfst_altlab.TransducerPair` object.
+        :param is_analyser: If true, then the generator FST is generated by inverting.  If false, then the analyser FST is generated by inverting.
+        :param search_cutoff: The maximum amount of time (in seconds) that the search will go on for.  The intention of a limit is to avoid search getting stuck.
+        :param default_distance: An optional function providing a distance between two strings. (see :py:meth:`hfst_altlab.TransducerPair.analyse`)
+        """
+        object = cls(
+            transducer,
+            transducer,
+            search_cutoff=search_cutoff,
+            default_distance=default_distance,
+        )
+        if is_analyser:
+            object.generator.invert()
+        else:
+            object.analyser.invert()
+        return object
+
+
+def decompress_foma(filename: Path | str):
+    """
+    Single wrapper around gzip. This is to increase readability.
+    This method is not used, but it is suggested as a way to debug the process of building a Transducer from a FOMA object.
+    """
+    return gzip.open(filename)

hfst_altlab/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/types.py

@@ -0,0 +1,231 @@
+from typing import NamedTuple, Tuple
+from hfst import is_diacritic
+
+
+class Analysis(NamedTuple):
+    """
+    An analysis of a wordform.  This class is backwards compatible with the ``hfst-optimized-lookup`` package.
+
+    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.
+    """
+
+    def __str__(self) -> str:
+        return f"{''.join(self.prefixes)}{self.lemma}{''.join(self.suffixes)}"
+
+
+def _parse_analysis(letters_and_tags: tuple[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 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),
+    )
+
+
+class FullAnalysis:
+    """
+    An analysis for a wordform.  Objects of this class include an analysis, a tuple of tokens (which provides information about flag diacritics), a weight (for weighted FST support), and a space to hold a standardized version of the wordform.
+    """
+
+    weight: float
+    """
+    The weight provided by the FST.  If the FST is not weighted, it is likely to be ``0.0``.
+    """
+
+    tokens: tuple[str, ...]
+    """
+    The real output of the FST.  Each element of the tuple is a symbol coming out of the FST.
+    The tuple includes flag diacritic symbols, which begin and end with an ``@`` character.  
+    We remove empty flag diacritic transitions (``@_EPSILON_SYMBOL_@``) to make the information usable and comparable with the output of the CLI tools.
+    """
+
+    analysis: Analysis
+    """
+    A grouping of the prefixes, lemma, and suffixes produced in the output of the FST.
+
+    The analysis is a split of the non-diacritic symbols in the tokens list.  We consider as the lemma the concatenation of all single-character symbols.  Prefixes are all multi-character symbols happening before the first single-character symbol, and suffixes are all multi-character symbols happening after that.
+
+    .. note:: The assumption of single-character symbols will conflict with multi-character emojis (for example, skin toned emojis). Although we are currently keeping this implementation, an alternative future approach would be to define prefixes as all multi-character symbols terminating in ``+``, suffixes as all multi-character symbols beginning with ``+``, and the lemma to be the concatenation of all other symbols.
+    """
+    standardized: str | None
+
+    @property
+    def prefixes(self) -> tuple[str, ...]:
+        """
+        For simplicity, prefixes can be accessed directly as if this were an :py:class:`hfst_altlab.Analysis` object.
+        """
+        return self.analysis.prefixes
+
+    @property
+    def lemma(self) -> str:
+        """
+        For simplicity, the lemma can be accessed directly as if this were an :py:class:`hfst_altlab.Analysis` object.
+        """
+        return self.analysis.lemma
+
+    @property
+    def suffixes(self) -> tuple[str, ...]:
+        """
+        For simplicity, suffixes can be accessed directly as if this were an :py:class:`hfst_altlab.Analysis` object.
+        """
+        return self.analysis.suffixes
+
+    def __init__(
+        self, weight: float, tokens: tuple[str, ...], standardized: str | None = None
+    ):
+        """
+        This object is not usually created directly by library users, but it is the output of some methods of :py:class:`hfst_altlab.TransducerFile` and :py:class:`hfst_altlab.TransducerPair`.
+        The information comes from direct calls to the ``hfst`` library.
+        :param weight: The weight of this analysis
+        :param tokens: The tuple of tokens coming from the FST.  It might contain empty symbols and epsilon diacritic transitions, which the FullAnalysis does not keep.
+        :param standardized: A standardized version of the associated wordform (only intrpoduced by :py:class:`hfst_altlab.TransducerPair` objects).  It is the result of providing the analysis to some other generator FST.
+        """
+        self.weight = weight
+        self.tokens = tuple(x for x in tokens if x and x != "@_EPSILON_SYMBOL_@")
+        self.analysis = _parse_analysis(self.tokens)
+        self.standardized = standardized
+
+    def __str__(self):
+        return f"FullAnalysis(weight={self.weight}, prefixes={self.analysis.prefixes}, lemma={self.analysis.lemma}, suffixes={self.analysis.suffixes})"
+
+    def __repr__(self):
+        return f"FullAnalysis(weight={self.weight}, tokens={self.tokens})"
+
+    def __eq__(self, other):
+        """
+        Note that equality between wordforms considers both weight and all tokens generated by the FST.  That is, there might be two Analysis objects such that ``a != b`` while ``a.lemma == b.lemma``, ``a.prefixes == b.prefixes``, and ``a.suffixes == b.suffixes``, if their flag diacritics are different.
+        """
+        if isinstance(other, self.__class__):
+            return self.weight == other.weight and self.tokens == other.tokens
+        else:
+            return False
+
+    def __hash__(self):
+        """
+        By providing a hashing function, we can place objects of this class into standard Python sets.
+        """
+        return hash((self.weight,) + self.tokens)
+
+    def as_fst_input(self) -> str:
+        return fst_output_format(self.tokens)
+
+
+class Wordform:
+    """
+    A wordform is the output of passing an analysis to a generator FST.
+    """
+
+    weight: float
+    """
+    For weighted FSTs, the weight of this particular wordform output.
+    """
+
+    tokens: tuple[str, ...]
+    """
+    The real output of the FST.  Each element of the tuple is a symbol coming out of the FST.
+    The tuple includes flag diacritic symbols, which begin and end with an ``@`` character.  
+    We remove empty flag diacritic transitions (``@_EPSILON_SYMBOL_@``) to make the information usable and comparable with the output of the CLI tools.
+    """
+
+    wordform: str
+    """
+    The wordform associated with the FST output, obtained by concatenating all the non-flag diacritic symbols in the tokens tuple.
+    """
+
+    def __init__(self, weight: float, tokens: tuple[str, ...]):
+        self.weight = weight
+        self.tokens = tokens
+        self.wordform = "".join(
+            x for x in tokens if x and not is_diacritic(x) and x != "@_EPSILON_SYMBOL_@"
+        )
+
+    def __str__(self):
+        """
+        The string representation of this object.  Equivalent to ``self.wordform``.
+        """
+        return self.wordform
+
+    def __repr__(self):
+        return f"Wordform(weight={self.weight}, wordform={self.wordform})"
+
+    def __eq__(self, other):
+        """
+        Note that equality between wordforms considers both weight and all tokens generated by the FST.  That is, there might be two Wordform objects such that ``a != b`` while ``str(a) == str(b)``, if their flag diacritics are different.
+        """
+        if isinstance(other, self.__class__):
+            return self.weight == other.weight and self.tokens == other.tokens
+        else:
+            return False
+
+    def __hash__(self):
+        """
+        By providing a hashing function, we can place objects of this class into standard Python sets.
+        """
+        return hash((self.weight,) + self.tokens)
+
+    def as_fst_input(self):
+        return self.wordform
+
+
+def as_fst_input(data: str | FullAnalysis | Wordform) -> str:
+    if isinstance(data, str):
+        return data
+    else:
+        return data.as_fst_input()
+
+
+def fst_output_format(tokens: tuple[str, ...]) -> str:
+    return "".join(x for x in tokens if not is_diacritic(x))

hfst_altlab-0.1.2.dist-info/METADATA

@@ -0,0 +1,37 @@
+Metadata-Version: 2.4
+Name: hfst-altlab
+Version: 0.1.2
+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
+Requires-Dist: hfst
+Dynamic: license-file
+
+hfst-altlab
+===========
+
+A wrapper on the [hfst][] python package, currently working as a replacement for [hfst-optimized-lookup][], built originally for [itwêwina][].
+
+This module helps to use both analyser and generator FSTs for multiple linguistic uses and language tools.
+
+[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
+
+[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
+
+[morphodict]: https://github.com/UAlbertaALTLab/morphodict

hfst_altlab-0.1.2.dist-info/RECORD

@@ -0,0 +1,8 @@
+hfst_altlab/__init__.py,sha256=dRYo0ZPmN3SoxWMCZGDNFrjNRHBthMKTxT-9s_gY_24,14571
+hfst_altlab/import_test.py,sha256=Fis-zc_Kw5pMkBFxey9Z9BYpdqRkHJmpam0d1BnsLZs,5472
+hfst_altlab/types.py,sha256=pwyveMoHgUsJc8t7M2GRjuzXL3r94WG3QAF7d9KLiGU,8604
+hfst_altlab-0.1.2.dist-info/licenses/LICENSE,sha256=xx0jnfkXJvxRnG63LTGOxlggYnIysveWIZ6H3PNdCrQ,11357
+hfst_altlab-0.1.2.dist-info/METADATA,sha256=WxLHUZuBYplTBETieYT_AjEu4EaB8i5CX1qG5p-nDfo,1409
+hfst_altlab-0.1.2.dist-info/WHEEL,sha256=wUyA8OaulRlbfwMtmQsvNngGrxQHAvkKcvRmdizlJi0,92
+hfst_altlab-0.1.2.dist-info/top_level.txt,sha256=gQi_zoi-ZXaVv7mohs7_OBSvnXW-2v0mBSTCb6wgK7E,12
+hfst_altlab-0.1.2.dist-info/RECORD,,

hfst_altlab-0.1.2.dist-info/WHEEL

@@ -0,0 +1,5 @@
+Wheel-Version: 1.0
+Generator: setuptools (80.10.2)
+Root-Is-Purelib: true
+Tag: py3-none-any
+

hfst_altlab-0.1.2.dist-info/licenses/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-0.1.2.dist-info/top_level.txt

@@ -0,0 +1 @@
+hfst_altlab