diff --git a/python/api/sudachipy.html b/python/api/sudachipy.html index a5203035..e33e8add 100644 --- a/python/api/sudachipy.html +++ b/python/api/sudachipy.html @@ -477,7 +477,7 @@

Morpheme
raw_surface($self) → str

–

-

Returns the substring of input text corresponding to the morpheme

+

Returns the substring of input text corresponding to the morpheme regardless the configured projection

@@ -511,7 +511,7 @@

Morpheme
surface($self) → str

–

-

Returns the substring of input text corresponding to the morpheme

+

Returns the substring of input text corresponding to the morpheme, or a projection if one is configured

diff --git a/python/api/sudachipy.morpheme.html b/python/api/sudachipy.morpheme.html index 97e04de4..1620c255 100644 --- a/python/api/sudachipy.morpheme.html +++ b/python/api/sudachipy.morpheme.html @@ -193,7 +193,7 @@

Note<
raw_surface($self) → str

–

-

Returns the substring of input text corresponding to the morpheme

+

Returns the substring of input text corresponding to the morpheme regardless the configured projection

@@ -227,7 +227,7 @@

Note<
surface($self) → str

–

-

Returns the substring of input text corresponding to the morpheme

+

Returns the substring of input text corresponding to the morpheme, or a projection if one is configured

diff --git a/python/searchindex.js b/python/searchindex.js index dca16d71..00ba7cae 100644 --- a/python/searchindex.js +++ b/python/searchindex.js @@ -1 +1 @@ -Search.setIndex({"docnames": ["api/sudachipy", "api/sudachipy.dictionary", "api/sudachipy.morpheme", "api/sudachipy.morphemelist", "api/sudachipy.tokenizer", "index", "topics/out_param", "topics/subsetting", "topics/wheels"], "filenames": ["api/sudachipy.rst", "api/sudachipy.dictionary.rst", "api/sudachipy.morpheme.rst", "api/sudachipy.morphemelist.rst", "api/sudachipy.tokenizer.rst", "index.rst", "topics/out_param.rst", "topics/subsetting.rst", "topics/wheels.rst"], "titles": ["sudachipy package", "sudachipy.dictionary package", "sudachipy.morpheme package", "sudachipy.morphemelist package", "sudachipy.tokenizer package", "Welcome to SudachiPy documentation!", "Output Parameters and Memory Reuse", "WordInfo subsetting", "Wheel Status"], "terms": {"class": [0, 1, 2, 3, 4], "system": [0, 1], "str": [0, 1, 2, 4], "none": [0, 1, 2, 4], "user": [0, 1], "list": [0, 1, 2, 3, 6], "project": [0, 1], "surfac": [0, 1, 2, 6, 7], "connectioncostplugin": 0, "oovproviderplugin": 0, "pathrewriteplugin": 0, "inputtextplugin": 0, "characterdefinitionfil": 0, "sourc": [0, 8], "rich": 0, "configur": 0, "object": [0, 1, 4], "field": [0, 1, 7], "pass": [0, 1, 2, 4, 6, 7], "here": 0, "overrid": 0, "default": [0, 1, 6, 7], "as_json": 0, "convert": 0, "thi": [0, 1, 2, 3, 4, 6, 7], "json": 0, "string": [0, 1, 7], "output": [0, 1, 2, 5], "follow": [0, 8], "result": [0, 2, 4, 6, 7], "instead": [0, 1, 2, 3, 4, 6], "its": [0, 1], "valu": [0, 1, 7], "option": [0, 2], "work": [0, 8], "pre": 0, "creat": [0, 1, 2, 4, 6, 7], "given": [0, 1], "well": 0, "The": [0, 6, 7, 8], "origin": [0, 1], "i": [0, 1, 2, 3, 4, 6, 7, 8], "avail": 0, "raw_surfac": [0, 2], "chitra": 0, "integr": 0, "normal": [0, 2], "read": [0, 2], "dictionary_and_surfac": 0, "normalized_and_surfac": 0, "normalized_noun": 0, "path": [0, 3], "one": [0, 1, 2, 4, 7], "three": 0, "small": 0, "core": 0, "notcor": 0, "If": [0, 1, 4, 7], "file": 0, "specifi": [0, 1], "doe": [0, 1], "exist": 0, "special": 0, "rais": [0, 6], "an": [0, 1, 2, 3, 6, 7], "error": 0, "you": [0, 3, 4, 6, 7, 8], "want": [0, 7], "us": [0, 1, 2, 3, 4, 6, 7, 8], "predefin": 0, "name": 0, "rel": 0, "e": [0, 7], "g": [0, 7], "same": 0, "we": [0, 8], "try": [0, 8], "load": [0, 1, 7], "from": [0, 1, 2, 3, 4, 8], "sudachidict_": 0, "instal": [0, 1, 8], "For": [0, 1], "exampl": [0, 1], "sudachidict_cor": 0, "maximum": 0, "number": [0, 3], "14": 0, "provid": [0, 1, 2, 8], "access": [0, 1], "grammar": [0, 1], "lexicon": [0, 1], "config_path": [0, 1], "resource_dir": [0, 1], "dict": [0, 1, 3], "dict_typ": [0, 1], "A": [0, 1, 3, 6], "sudachi": [0, 1, 2, 4], "close": [0, 1], "self": [0, 1, 2, 3, 4], "mode": [0, 1, 2, 4, 6, 7], "c": [0, 1], "paramet": [0, 1, 2, 4, 5, 7], "": [0, 1, 6], "split": [0, 1, 2, 4, 6, 7], "onli": [0, 1, 7, 8], "subset": [0, 1, 5], "see": [0, 1, 2, 4], "http": [0, 1, 2, 4], "worksappl": [0, 1, 2, 4], "github": [0, 1, 2, 4], "io": [0, 1, 2, 4], "r": [0, 1, 2, 4], "python": [0, 1, 2, 4], "topic": [0, 1, 2, 4], "html": [0, 1, 2, 4], "lookup": [0, 1], "out": [0, 1, 2, 4, 6], "morphemelist": [0, 1, 2, 4, 5, 6], "look": [0, 1], "up": [0, 1], "binari": [0, 1], "without": [0, 1, 7], "perform": [0, 1, 7], "analysi": [0, 1, 4, 6], "all": [0, 1, 7], "ar": [0, 1, 2, 7, 8], "return": [0, 1, 2, 3, 7], "last": [0, 1], "search": [0, 1, 5], "first": [0, 1], "insid": [0, 1], "order": [0, 1], "which": [0, 1, 2, 8], "index": [0, 1, 2, 5], "find": [0, 1], "reus": [0, 1, 5], "new": [0, 1, 2, 4, 6], "out_param": [0, 1, 2, 4], "detail": [0, 1, 4], "type": [0, 1, 2], "pos_match": [0, 1], "target": [0, 1], "po": [0, 1, 2, 7], "matcher": [0, 1], "function": [0, 1], "must": [0, 1], "whether": [0, 1, 2], "should": [0, 1, 6, 8], "match": [0, 1], "contain": [0, 1, 8], "partial": [0, 1], "By": [0, 1, 6, 7], "mean": [0, 1], "possibl": [0, 1, 6, 7], "omit": [0, 1, 7], "sentinel": [0, 1], "ani": [0, 1, 2, 7], "\u540d\u8a5e": [0, 1], "noun": [0, 1], "\u7d42\u6b62\u5f62": [0, 1], "\u4e00\u822c": [0, 1], "word": [0, 1, 2, 7], "conjug": [0, 1, 2], "form": [0, 1, 2, 7], "can": [0, 1, 4, 6, 7, 8], "either": [0, 1], "callabl": [0, 1], "tupl": [0, 1, 2], "pos_of": [0, 1], "get": [0, 1], "id": [0, 1, 2], "pre_token": [0, 1], "handler": [0, 1], "pretoken": [0, 1], "huggingfac": [0, 1], "compat": [0, 1, 8], "requir": [0, 1, 7], "set": [0, 1, 7], "ask": [0, 1, 7], "custom": [0, 1], "transform": [0, 1], "It": [0, 1, 7], "int": [0, 1, 2, 3], "normalizedstr": [0, 1], "com": [0, 1], "blob": [0, 1], "master": [0, 1], "bind": [0, 1], "custom_compon": [0, 1], "py": [0, 1], "noth": [0, 1], "wa": [0, 1], "simpli": [0, 1], "represent": [0, 1], "document": [0, 1], "support": [0, 1, 6, 8], "unit": 0, "text": [0, 2, 4, 7], "short": 0, "b": [0, 7], "middl": 0, "long": 0, "version": [0, 4], "logger": [0, 4], "break": [0, 4], "0": [0, 4, 6], "5": [0, 4], "had": [0, 4], "accept": [0, 4, 7], "ignor": [0, 4], "analyz": [0, 4], "deprec": [0, 1, 2, 3, 4], "creation": [0, 4], "time": [0, 4, 8], "differ": [0, 4], "need": [0, 3, 4, 7], "multi": [0, 4], "level": [0, 2, 4], "prefer": [0, 4], "method": [0, 2, 3, 4, 6, 7], "written": [0, 4], "empti": [0, 2, 3, 7], "get_internal_cost": [0, 3], "total": [0, 3], "cost": [0, 3], "size": [0, 3], "get_word_info": [0, 2], "begin": [0, 2], "input": [0, 2, 7], "dictionary_form": [0, 2, 7], "dictionary_id": [0, 2], "belong": [0, 2], "end": [0, 2], "info": [0, 2], "is_oov": [0, 2], "bool": [0, 2], "vocabulari": [0, 2], "normalized_form": [0, 2, 7], "part_of_speech": [0, 2], "part": [0, 2, 7], "speech": [0, 2, 7], "six": [0, 2], "element": [0, 2], "four": [0, 2], "part_of_speech_id": [0, 2], "substr": [0, 2], "correspond": [0, 2], "reading_form": [0, 2, 7], "add_singl": [0, 2], "fals": [0, 2], "sub": [0, 2], "write": [0, 2], "morhpemelist": [0, 2], "more": [0, 2], "inform": [0, 2], "invalid": [0, 2, 6], "current": [0, 2], "hasn": [0, 2], "t": [0, 2, 8], "produc": [0, 2, 7], "when": [0, 2, 6, 7, 8], "synonym_group_id": [0, 2, 7], "synonym": [0, 2], "group": [0, 2], "word_id": [0, 2], "a_unit_split": 0, "b_unit_split": 0, "dictionary_form_word_id": 0, "head_word_length": 0, "length": 0, "pos_id": [0, 7], "word_structur": [0, 7], "import": [1, 2, 3, 4], "config": [1, 5], "splitmod": [1, 2, 4, 5, 6, 7], "token": [1, 3, 5, 6, 7], "morphem": [1, 3, 4, 5, 6, 7], "wordinfo": [2, 5], "dictionari": [2, 3, 5, 7], "also": [4, 6], "memori": 5, "wheel": 5, "statu": 5, "packag": [5, 8], "note": 5, "modul": 5, "content": 5, "page": 5, "sudachipi": [6, 7], "each": [6, 7], "run": 6, "That": 6, "incur": 6, "measur": 6, "alloc": 6, "overhead": 6, "multipl": 6, "basic": 6, "usag": 6, "pattern": 6, "tok": 6, "dic": [6, 7], "line": 6, "data": 6, "process": 6, "replac": 6, "old": 6, "case": 6, "In": 6, "care": 6, "becaus": 6, "refer": 6, "parent": 6, "ml1": 6, "\u5916\u56fd\u4eba\u53c2\u653f\u6a29": 6, "subl1": 6, "someth": 6, "except": 6, "suachi": 7, "To": 7, "do": 7, "repres": 7, "allow": 7, "slice": 7, "affect": 7, "flag": 7, "tag": 7, "splits_a": 7, "splits_b": 7, "non": 7, "automat": 7, "implicitli": 7, "becom": 7, "includ": 7, "incorrect": 7, "warn": 7, "test": [7, 8], "ensur": 7, "build": 8, "platform": 8, "amd64": 8, "x86_64": 8, "universal2": 8, "arm64": 8, "fix": 8, "bug": 8, "problem": 8, "report": 8, "best": 8, "effort": 8, "manner": 8, "take": 8, "unspecifi": 8, "amount": 8, "welcom": 8, "contribut": 8, "them": 8, "architectur": 8, "moment": 8, "built": 8, "profil": 8, "guid": 8, "optim": 8, "probabl": 8, "faster": 8, "than": 8, "manaulli": 8, "manylinux": 8, "most": 8, "distribut": 8, "witout": 8, "pgo": 8, "have": 8, "yourself": 8, "don": 8, "x86": 8, "situat": 8, "similar": 8, "even": 8, "less": 8, "both": 8, "intel": 8, "arm": 8, "base": 8, "mac": 8, "ci": 8, "basi": 8}, "objects": {"sudachipy": [[0, 0, 1, "", "Dictionary"], [0, 0, 1, "", "Morpheme"], [0, 0, 1, "", "MorphemeList"], [0, 0, 1, "", "SplitMode"], [0, 0, 1, "", "Tokenizer"], [0, 0, 1, "", "WordInfo"], [1, 3, 0, "-", "dictionary"], [2, 3, 0, "-", "morpheme"], [3, 3, 0, "-", "morphemelist"], [4, 3, 0, "-", "tokenizer"]], "sudachipy.Dictionary": [[0, 1, 1, "", "close"], [0, 1, 1, "", "create"], [0, 1, 1, "", "lookup"], [0, 1, 1, "", "pos_matcher"], [0, 1, 1, "", "pos_of"], [0, 1, 1, "", "pre_tokenizer"]], "sudachipy.Morpheme": [[0, 1, 1, "", "begin"], [0, 1, 1, "", "dictionary_form"], [0, 1, 1, "", "dictionary_id"], [0, 1, 1, "", "end"], [0, 1, 1, "", "get_word_info"], [0, 1, 1, "", "is_oov"], [0, 1, 1, "", "normalized_form"], [0, 1, 1, "", "part_of_speech"], [0, 1, 1, "", "part_of_speech_id"], [0, 1, 1, "", "raw_surface"], [0, 1, 1, "", "reading_form"], [0, 1, 1, "", "split"], [0, 1, 1, "", "surface"], [0, 1, 1, "", "synonym_group_ids"], [0, 1, 1, "", "word_id"]], "sudachipy.MorphemeList": [[0, 1, 1, "", "empty"], [0, 1, 1, "", "get_internal_cost"], [0, 1, 1, "", "size"]], "sudachipy.Tokenizer": [[0, 2, 1, "", "SplitMode"], [0, 1, 1, "", "tokenize"]], "sudachipy.WordInfo": [[0, 2, 1, "", "a_unit_split"], [0, 2, 1, "", "b_unit_split"], [0, 2, 1, "", "dictionary_form"], [0, 2, 1, "", "dictionary_form_word_id"], [0, 2, 1, "", "head_word_length"], [0, 1, 1, "", "length"], [0, 2, 1, "", "normalized_form"], [0, 2, 1, "", "pos_id"], [0, 2, 1, "", "reading_form"], [0, 2, 1, "", "surface"], [0, 2, 1, "", "synonym_group_ids"], [0, 2, 1, "", "word_structure"]], "sudachipy.config": [[0, 0, 1, "", "Config"]], "sudachipy.config.Config": [[0, 1, 1, "", "as_jsons"], [0, 2, 1, "", "projection"], [0, 2, 1, "", "system"], [0, 2, 1, "", "user"]], "sudachipy.dictionary": [[1, 0, 1, "", "Dictionary"]], "sudachipy.dictionary.Dictionary": [[1, 1, 1, "", "close"], [1, 1, 1, "", "create"], [1, 1, 1, "", "lookup"], [1, 1, 1, "", "pos_matcher"], [1, 1, 1, "", "pos_of"], [1, 1, 1, "", "pre_tokenizer"]], "sudachipy.morpheme": [[2, 0, 1, "", "Morpheme"]], "sudachipy.morpheme.Morpheme": [[2, 1, 1, "", "begin"], [2, 1, 1, "", "dictionary_form"], [2, 1, 1, "", "dictionary_id"], [2, 1, 1, "", "end"], [2, 1, 1, "", "get_word_info"], [2, 1, 1, "", "is_oov"], [2, 1, 1, "", "normalized_form"], [2, 1, 1, "", "part_of_speech"], [2, 1, 1, "", "part_of_speech_id"], [2, 1, 1, "", "raw_surface"], [2, 1, 1, "", "reading_form"], [2, 1, 1, "", "split"], [2, 1, 1, "", "surface"], [2, 1, 1, "", "synonym_group_ids"], [2, 1, 1, "", "word_id"]], "sudachipy.morphemelist": [[3, 0, 1, "", "MorphemeList"]], "sudachipy.morphemelist.MorphemeList": [[3, 1, 1, "", "empty"], [3, 1, 1, "", "get_internal_cost"], [3, 1, 1, "", "size"]], "sudachipy.tokenizer": [[4, 0, 1, "", "Tokenizer"]], "sudachipy.tokenizer.Tokenizer": [[4, 2, 1, "", "SplitMode"], [4, 1, 1, "", "tokenize"]]}, "objtypes": {"0": "py:class", "1": "py:method", "2": "py:attribute", "3": "py:module"}, "objnames": {"0": ["py", "class", "Python class"], "1": ["py", "method", "Python method"], "2": ["py", "attribute", "Python attribute"], "3": ["py", "module", "Python module"]}, "titleterms": {"sudachipi": [0, 1, 2, 3, 4, 5], "packag": [0, 1, 2, 3, 4], "config": 0, "dictionari": [0, 1], "splitmod": 0, "token": [0, 4], "morphem": [0, 2], "wordinfo": [0, 7], "note": [1, 2, 3, 4], "modul": [1, 2, 3, 4], "content": [1, 2, 3, 4], "morphemelist": 3, "welcom": 5, "document": 5, "topic": 5, "api": 5, "refer": 5, "indic": 5, "tabl": 5, "output": 6, "paramet": 6, "memori": 6, "reus": 6, "subset": 7, "wheel": 8, "statu": 8, "linux": 8, "window": 8, "maco": 8}, "envversion": {"sphinx.domains.c": 3, "sphinx.domains.changeset": 1, "sphinx.domains.citation": 1, "sphinx.domains.cpp": 9, "sphinx.domains.index": 1, "sphinx.domains.javascript": 3, "sphinx.domains.math": 2, "sphinx.domains.python": 4, "sphinx.domains.rst": 2, "sphinx.domains.std": 2, "sphinx.ext.viewcode": 1, "sphinx.ext.todo": 2, "sphinx": 60}, "alltitles": {"sudachipy package": [[0, "sudachipy-package"]], "config.Config": [[0, "config-config"]], "Dictionary": [[0, "dictionary"]], "SplitMode": [[0, "splitmode"]], "Tokenizer": [[0, "tokenizer"]], "Morpheme": [[0, "morpheme"]], "WordInfo": [[0, "wordinfo"]], "sudachipy.dictionary package": [[1, "sudachipy-dictionary-package"]], "Note": [[1, "note"], [2, "note"], [3, "note"], [4, "note"]], "Module contents": [[1, "module-sudachipy.dictionary"], [2, "module-sudachipy.morpheme"], [3, "module-sudachipy.morphemelist"], [4, "module-sudachipy.tokenizer"]], "sudachipy.morpheme package": [[2, "sudachipy-morpheme-package"]], "sudachipy.morphemelist package": [[3, "sudachipy-morphemelist-package"]], "sudachipy.tokenizer package": [[4, "sudachipy-tokenizer-package"]], "Welcome to SudachiPy documentation!": [[5, "welcome-to-sudachipy-documentation"]], "Topics": [[5, null]], "API Reference:": [[5, null]], "Indices and tables": [[5, "indices-and-tables"]], "Output Parameters and Memory Reuse": [[6, "output-parameters-and-memory-reuse"]], "WordInfo subsetting": [[7, "wordinfo-subsetting"]], "Wheel Status": [[8, "wheel-status"]], "Linux": [[8, "linux"]], "Windows": [[8, "windows"]], "macOS": [[8, "macos"]]}, "indexentries": {"config (class in sudachipy.config)": [[0, "sudachipy.config.Config"]], "dictionary (class in sudachipy)": [[0, "sudachipy.Dictionary"]], "morpheme (class in sudachipy)": [[0, "sudachipy.Morpheme"]], "morphemelist (class in sudachipy)": [[0, "sudachipy.MorphemeList"]], "splitmode (class in sudachipy)": [[0, "sudachipy.SplitMode"]], "splitmode (sudachipy.tokenizer attribute)": [[0, "sudachipy.Tokenizer.SplitMode"]], "tokenizer (class in sudachipy)": [[0, "sudachipy.Tokenizer"]], "wordinfo (class in sudachipy)": [[0, "sudachipy.WordInfo"]], "a_unit_split (sudachipy.wordinfo attribute)": [[0, "sudachipy.WordInfo.a_unit_split"]], "as_jsons() (sudachipy.config.config method)": [[0, "sudachipy.config.Config.as_jsons"]], "b_unit_split (sudachipy.wordinfo attribute)": [[0, "sudachipy.WordInfo.b_unit_split"]], "begin() (sudachipy.morpheme method)": [[0, "sudachipy.Morpheme.begin"]], "close() (sudachipy.dictionary method)": [[0, "sudachipy.Dictionary.close"]], "create() (sudachipy.dictionary method)": [[0, "sudachipy.Dictionary.create"]], "dictionary_form (sudachipy.wordinfo attribute)": [[0, "sudachipy.WordInfo.dictionary_form"]], "dictionary_form() (sudachipy.morpheme method)": [[0, "sudachipy.Morpheme.dictionary_form"]], "dictionary_form_word_id (sudachipy.wordinfo attribute)": [[0, "sudachipy.WordInfo.dictionary_form_word_id"]], "dictionary_id() (sudachipy.morpheme method)": [[0, "sudachipy.Morpheme.dictionary_id"]], "empty() (sudachipy.morphemelist method)": [[0, "sudachipy.MorphemeList.empty"]], "end() (sudachipy.morpheme method)": [[0, "sudachipy.Morpheme.end"]], "get_internal_cost() (sudachipy.morphemelist method)": [[0, "sudachipy.MorphemeList.get_internal_cost"]], "get_word_info() (sudachipy.morpheme method)": [[0, "sudachipy.Morpheme.get_word_info"]], "head_word_length (sudachipy.wordinfo attribute)": [[0, "sudachipy.WordInfo.head_word_length"]], "is_oov() (sudachipy.morpheme method)": [[0, "sudachipy.Morpheme.is_oov"]], "length() (sudachipy.wordinfo method)": [[0, "sudachipy.WordInfo.length"]], "lookup() (sudachipy.dictionary method)": [[0, "sudachipy.Dictionary.lookup"]], "normalized_form (sudachipy.wordinfo attribute)": [[0, "sudachipy.WordInfo.normalized_form"]], "normalized_form() (sudachipy.morpheme method)": [[0, "sudachipy.Morpheme.normalized_form"]], "part_of_speech() (sudachipy.morpheme method)": [[0, "sudachipy.Morpheme.part_of_speech"]], "part_of_speech_id() (sudachipy.morpheme method)": [[0, "sudachipy.Morpheme.part_of_speech_id"]], "pos_id (sudachipy.wordinfo attribute)": [[0, "sudachipy.WordInfo.pos_id"]], "pos_matcher() (sudachipy.dictionary method)": [[0, "sudachipy.Dictionary.pos_matcher"]], "pos_of() (sudachipy.dictionary method)": [[0, "sudachipy.Dictionary.pos_of"]], "pre_tokenizer() (sudachipy.dictionary method)": [[0, "sudachipy.Dictionary.pre_tokenizer"]], "projection (sudachipy.config.config attribute)": [[0, "sudachipy.config.Config.projection"]], "raw_surface() (sudachipy.morpheme method)": [[0, "sudachipy.Morpheme.raw_surface"]], "reading_form (sudachipy.wordinfo attribute)": [[0, "sudachipy.WordInfo.reading_form"]], "reading_form() (sudachipy.morpheme method)": [[0, "sudachipy.Morpheme.reading_form"]], "size() (sudachipy.morphemelist method)": [[0, "sudachipy.MorphemeList.size"]], "split() (sudachipy.morpheme method)": [[0, "sudachipy.Morpheme.split"]], "surface (sudachipy.wordinfo attribute)": [[0, "sudachipy.WordInfo.surface"]], "surface() (sudachipy.morpheme method)": [[0, "sudachipy.Morpheme.surface"]], "synonym_group_ids (sudachipy.wordinfo attribute)": [[0, "sudachipy.WordInfo.synonym_group_ids"]], "synonym_group_ids() (sudachipy.morpheme method)": [[0, "sudachipy.Morpheme.synonym_group_ids"]], "system (sudachipy.config.config attribute)": [[0, "sudachipy.config.Config.system"]], "tokenize() (sudachipy.tokenizer method)": [[0, "sudachipy.Tokenizer.tokenize"]], "user (sudachipy.config.config attribute)": [[0, "sudachipy.config.Config.user"]], "word_id() (sudachipy.morpheme method)": [[0, "sudachipy.Morpheme.word_id"]], "word_structure (sudachipy.wordinfo attribute)": [[0, "sudachipy.WordInfo.word_structure"]], "dictionary (class in sudachipy.dictionary)": [[1, "sudachipy.dictionary.Dictionary"]], "close() (sudachipy.dictionary.dictionary method)": [[1, "sudachipy.dictionary.Dictionary.close"]], "create() (sudachipy.dictionary.dictionary method)": [[1, "sudachipy.dictionary.Dictionary.create"]], "lookup() (sudachipy.dictionary.dictionary method)": [[1, "sudachipy.dictionary.Dictionary.lookup"]], "module": [[1, "module-sudachipy.dictionary"], [2, "module-sudachipy.morpheme"], [3, "module-sudachipy.morphemelist"], [4, "module-sudachipy.tokenizer"]], "pos_matcher() (sudachipy.dictionary.dictionary method)": [[1, "sudachipy.dictionary.Dictionary.pos_matcher"]], "pos_of() (sudachipy.dictionary.dictionary method)": [[1, "sudachipy.dictionary.Dictionary.pos_of"]], "pre_tokenizer() (sudachipy.dictionary.dictionary method)": [[1, "sudachipy.dictionary.Dictionary.pre_tokenizer"]], "sudachipy.dictionary": [[1, "module-sudachipy.dictionary"]], "morpheme (class in sudachipy.morpheme)": [[2, "sudachipy.morpheme.Morpheme"]], "begin() (sudachipy.morpheme.morpheme method)": [[2, "sudachipy.morpheme.Morpheme.begin"]], "dictionary_form() (sudachipy.morpheme.morpheme method)": [[2, "sudachipy.morpheme.Morpheme.dictionary_form"]], "dictionary_id() (sudachipy.morpheme.morpheme method)": [[2, "sudachipy.morpheme.Morpheme.dictionary_id"]], "end() (sudachipy.morpheme.morpheme method)": [[2, "sudachipy.morpheme.Morpheme.end"]], "get_word_info() (sudachipy.morpheme.morpheme method)": [[2, "sudachipy.morpheme.Morpheme.get_word_info"]], "is_oov() (sudachipy.morpheme.morpheme method)": [[2, "sudachipy.morpheme.Morpheme.is_oov"]], "normalized_form() (sudachipy.morpheme.morpheme method)": [[2, "sudachipy.morpheme.Morpheme.normalized_form"]], "part_of_speech() (sudachipy.morpheme.morpheme method)": [[2, "sudachipy.morpheme.Morpheme.part_of_speech"]], "part_of_speech_id() (sudachipy.morpheme.morpheme method)": [[2, "sudachipy.morpheme.Morpheme.part_of_speech_id"]], "raw_surface() (sudachipy.morpheme.morpheme method)": [[2, "sudachipy.morpheme.Morpheme.raw_surface"]], "reading_form() (sudachipy.morpheme.morpheme method)": [[2, "sudachipy.morpheme.Morpheme.reading_form"]], "split() (sudachipy.morpheme.morpheme method)": [[2, "sudachipy.morpheme.Morpheme.split"]], "sudachipy.morpheme": [[2, "module-sudachipy.morpheme"]], "surface() (sudachipy.morpheme.morpheme method)": [[2, "sudachipy.morpheme.Morpheme.surface"]], "synonym_group_ids() (sudachipy.morpheme.morpheme method)": [[2, "sudachipy.morpheme.Morpheme.synonym_group_ids"]], "word_id() (sudachipy.morpheme.morpheme method)": [[2, "sudachipy.morpheme.Morpheme.word_id"]], "morphemelist (class in sudachipy.morphemelist)": [[3, "sudachipy.morphemelist.MorphemeList"]], "empty() (sudachipy.morphemelist.morphemelist method)": [[3, "sudachipy.morphemelist.MorphemeList.empty"]], "get_internal_cost() (sudachipy.morphemelist.morphemelist method)": [[3, "sudachipy.morphemelist.MorphemeList.get_internal_cost"]], "size() (sudachipy.morphemelist.morphemelist method)": [[3, "sudachipy.morphemelist.MorphemeList.size"]], "sudachipy.morphemelist": [[3, "module-sudachipy.morphemelist"]], "splitmode (sudachipy.tokenizer.tokenizer attribute)": [[4, "sudachipy.tokenizer.Tokenizer.SplitMode"]], "tokenizer (class in sudachipy.tokenizer)": [[4, "sudachipy.tokenizer.Tokenizer"]], "sudachipy.tokenizer": [[4, "module-sudachipy.tokenizer"]], "tokenize() (sudachipy.tokenizer.tokenizer method)": [[4, "sudachipy.tokenizer.Tokenizer.tokenize"]]}}) \ No newline at end of file +Search.setIndex({"docnames": ["api/sudachipy", "api/sudachipy.dictionary", "api/sudachipy.morpheme", "api/sudachipy.morphemelist", "api/sudachipy.tokenizer", "index", "topics/out_param", "topics/subsetting", "topics/wheels"], "filenames": ["api/sudachipy.rst", "api/sudachipy.dictionary.rst", "api/sudachipy.morpheme.rst", "api/sudachipy.morphemelist.rst", "api/sudachipy.tokenizer.rst", "index.rst", "topics/out_param.rst", "topics/subsetting.rst", "topics/wheels.rst"], "titles": ["sudachipy package", "sudachipy.dictionary package", "sudachipy.morpheme package", "sudachipy.morphemelist package", "sudachipy.tokenizer package", "Welcome to SudachiPy documentation!", "Output Parameters and Memory Reuse", "WordInfo subsetting", "Wheel Status"], "terms": {"class": [0, 1, 2, 3, 4], "system": [0, 1], "str": [0, 1, 2, 4], "none": [0, 1, 2, 4], "user": [0, 1], "list": [0, 1, 2, 3, 6], "project": [0, 1, 2], "surfac": [0, 1, 2, 6, 7], "connectioncostplugin": 0, "oovproviderplugin": 0, "pathrewriteplugin": 0, "inputtextplugin": 0, "characterdefinitionfil": 0, "sourc": [0, 8], "rich": 0, "configur": [0, 2], "object": [0, 1, 4], "field": [0, 1, 7], "pass": [0, 1, 2, 4, 6, 7], "here": 0, "overrid": 0, "default": [0, 1, 6, 7], "as_json": 0, "convert": 0, "thi": [0, 1, 2, 3, 4, 6, 7], "json": 0, "string": [0, 1, 7], "output": [0, 1, 2, 5], "follow": [0, 8], "result": [0, 2, 4, 6, 7], "instead": [0, 1, 2, 3, 4, 6], "its": [0, 1], "valu": [0, 1, 7], "option": [0, 2], "work": [0, 8], "pre": 0, "creat": [0, 1, 2, 4, 6, 7], "given": [0, 1], "well": 0, "The": [0, 6, 7, 8], "origin": [0, 1], "i": [0, 1, 2, 3, 4, 6, 7, 8], "avail": 0, "raw_surfac": [0, 2], "chitra": 0, "integr": 0, "normal": [0, 2], "read": [0, 2], "dictionary_and_surfac": 0, "normalized_and_surfac": 0, "normalized_noun": 0, "path": [0, 3], "one": [0, 1, 2, 4, 7], "three": 0, "small": 0, "core": 0, "notcor": 0, "If": [0, 1, 4, 7], "file": 0, "specifi": [0, 1], "doe": [0, 1], "exist": 0, "special": 0, "rais": [0, 6], "an": [0, 1, 2, 3, 6, 7], "error": 0, "you": [0, 3, 4, 6, 7, 8], "want": [0, 7], "us": [0, 1, 2, 3, 4, 6, 7, 8], "predefin": 0, "name": 0, "rel": 0, "e": [0, 7], "g": [0, 7], "same": 0, "we": [0, 8], "try": [0, 8], "load": [0, 1, 7], "from": [0, 1, 2, 3, 4, 8], "sudachidict_": 0, "instal": [0, 1, 8], "For": [0, 1], "exampl": [0, 1], "sudachidict_cor": 0, "maximum": 0, "number": [0, 3], "14": 0, "provid": [0, 1, 2, 8], "access": [0, 1], "grammar": [0, 1], "lexicon": [0, 1], "config_path": [0, 1], "resource_dir": [0, 1], "dict": [0, 1, 3], "dict_typ": [0, 1], "A": [0, 1, 3, 6], "sudachi": [0, 1, 2, 4], "close": [0, 1], "self": [0, 1, 2, 3, 4], "mode": [0, 1, 2, 4, 6, 7], "c": [0, 1], "paramet": [0, 1, 2, 4, 5, 7], "": [0, 1, 6], "split": [0, 1, 2, 4, 6, 7], "onli": [0, 1, 7, 8], "subset": [0, 1, 5], "see": [0, 1, 2, 4], "http": [0, 1, 2, 4], "worksappl": [0, 1, 2, 4], "github": [0, 1, 2, 4], "io": [0, 1, 2, 4], "r": [0, 1, 2, 4], "python": [0, 1, 2, 4], "topic": [0, 1, 2, 4], "html": [0, 1, 2, 4], "lookup": [0, 1], "out": [0, 1, 2, 4, 6], "morphemelist": [0, 1, 2, 4, 5, 6], "look": [0, 1], "up": [0, 1], "binari": [0, 1], "without": [0, 1, 7], "perform": [0, 1, 7], "analysi": [0, 1, 4, 6], "all": [0, 1, 7], "ar": [0, 1, 2, 7, 8], "return": [0, 1, 2, 3, 7], "last": [0, 1], "search": [0, 1, 5], "first": [0, 1], "insid": [0, 1], "order": [0, 1], "which": [0, 1, 2, 8], "index": [0, 1, 2, 5], "find": [0, 1], "reus": [0, 1, 5], "new": [0, 1, 2, 4, 6], "out_param": [0, 1, 2, 4], "detail": [0, 1, 4], "type": [0, 1, 2], "pos_match": [0, 1], "target": [0, 1], "po": [0, 1, 2, 7], "matcher": [0, 1], "function": [0, 1], "must": [0, 1], "whether": [0, 1, 2], "should": [0, 1, 6, 8], "match": [0, 1], "contain": [0, 1, 8], "partial": [0, 1], "By": [0, 1, 6, 7], "mean": [0, 1], "possibl": [0, 1, 6, 7], "omit": [0, 1, 7], "sentinel": [0, 1], "ani": [0, 1, 2, 7], "\u540d\u8a5e": [0, 1], "noun": [0, 1], "\u7d42\u6b62\u5f62": [0, 1], "\u4e00\u822c": [0, 1], "word": [0, 1, 2, 7], "conjug": [0, 1, 2], "form": [0, 1, 2, 7], "can": [0, 1, 4, 6, 7, 8], "either": [0, 1], "callabl": [0, 1], "tupl": [0, 1, 2], "pos_of": [0, 1], "get": [0, 1], "id": [0, 1, 2], "pre_token": [0, 1], "handler": [0, 1], "pretoken": [0, 1], "huggingfac": [0, 1], "compat": [0, 1, 8], "requir": [0, 1, 7], "set": [0, 1, 7], "ask": [0, 1, 7], "custom": [0, 1], "transform": [0, 1], "It": [0, 1, 7], "int": [0, 1, 2, 3], "normalizedstr": [0, 1], "com": [0, 1], "blob": [0, 1], "master": [0, 1], "bind": [0, 1], "custom_compon": [0, 1], "py": [0, 1], "noth": [0, 1], "wa": [0, 1], "simpli": [0, 1], "represent": [0, 1], "document": [0, 1], "support": [0, 1, 6, 8], "unit": 0, "text": [0, 2, 4, 7], "short": 0, "b": [0, 7], "middl": 0, "long": 0, "version": [0, 4], "logger": [0, 4], "break": [0, 4], "0": [0, 4, 6], "5": [0, 4], "had": [0, 4], "accept": [0, 4, 7], "ignor": [0, 4], "analyz": [0, 4], "deprec": [0, 1, 2, 3, 4], "creation": [0, 4], "time": [0, 4, 8], "differ": [0, 4], "need": [0, 3, 4, 7], "multi": [0, 4], "level": [0, 2, 4], "prefer": [0, 4], "method": [0, 2, 3, 4, 6, 7], "written": [0, 4], "empti": [0, 2, 3, 7], "get_internal_cost": [0, 3], "total": [0, 3], "cost": [0, 3], "size": [0, 3], "get_word_info": [0, 2], "begin": [0, 2], "input": [0, 2, 7], "dictionary_form": [0, 2, 7], "dictionary_id": [0, 2], "belong": [0, 2], "end": [0, 2], "info": [0, 2], "is_oov": [0, 2], "bool": [0, 2], "vocabulari": [0, 2], "normalized_form": [0, 2, 7], "part_of_speech": [0, 2], "part": [0, 2, 7], "speech": [0, 2, 7], "six": [0, 2], "element": [0, 2], "four": [0, 2], "part_of_speech_id": [0, 2], "substr": [0, 2], "correspond": [0, 2], "regardless": [0, 2], "reading_form": [0, 2, 7], "add_singl": [0, 2], "fals": [0, 2], "sub": [0, 2], "write": [0, 2], "morhpemelist": [0, 2], "more": [0, 2], "inform": [0, 2], "invalid": [0, 2, 6], "current": [0, 2], "hasn": [0, 2], "t": [0, 2, 8], "produc": [0, 2, 7], "when": [0, 2, 6, 7, 8], "synonym_group_id": [0, 2, 7], "synonym": [0, 2], "group": [0, 2], "word_id": [0, 2], "a_unit_split": 0, "b_unit_split": 0, "dictionary_form_word_id": 0, "head_word_length": 0, "length": 0, "pos_id": [0, 7], "word_structur": [0, 7], "import": [1, 2, 3, 4], "config": [1, 5], "splitmod": [1, 2, 4, 5, 6, 7], "token": [1, 3, 5, 6, 7], "morphem": [1, 3, 4, 5, 6, 7], "wordinfo": [2, 5], "dictionari": [2, 3, 5, 7], "also": [4, 6], "memori": 5, "wheel": 5, "statu": 5, "packag": [5, 8], "note": 5, "modul": 5, "content": 5, "page": 5, "sudachipi": [6, 7], "each": [6, 7], "run": 6, "That": 6, "incur": 6, "measur": 6, "alloc": 6, "overhead": 6, "multipl": 6, "basic": 6, "usag": 6, "pattern": 6, "tok": 6, "dic": [6, 7], "line": 6, "data": 6, "process": 6, "replac": 6, "old": 6, "case": 6, "In": 6, "care": 6, "becaus": 6, "refer": 6, "parent": 6, "ml1": 6, "\u5916\u56fd\u4eba\u53c2\u653f\u6a29": 6, "subl1": 6, "someth": 6, "except": 6, "suachi": 7, "To": 7, "do": 7, "repres": 7, "allow": 7, "slice": 7, "affect": 7, "flag": 7, "tag": 7, "splits_a": 7, "splits_b": 7, "non": 7, "automat": 7, "implicitli": 7, "becom": 7, "includ": 7, "incorrect": 7, "warn": 7, "test": [7, 8], "ensur": 7, "build": 8, "platform": 8, "amd64": 8, "x86_64": 8, "universal2": 8, "arm64": 8, "fix": 8, "bug": 8, "problem": 8, "report": 8, "best": 8, "effort": 8, "manner": 8, "take": 8, "unspecifi": 8, "amount": 8, "welcom": 8, "contribut": 8, "them": 8, "architectur": 8, "moment": 8, "built": 8, "profil": 8, "guid": 8, "optim": 8, "probabl": 8, "faster": 8, "than": 8, "manaulli": 8, "manylinux": 8, "most": 8, "distribut": 8, "witout": 8, "pgo": 8, "have": 8, "yourself": 8, "don": 8, "x86": 8, "situat": 8, "similar": 8, "even": 8, "less": 8, "both": 8, "intel": 8, "arm": 8, "base": 8, "mac": 8, "ci": 8, "basi": 8}, "objects": {"sudachipy": [[0, 0, 1, "", "Dictionary"], [0, 0, 1, "", "Morpheme"], [0, 0, 1, "", "MorphemeList"], [0, 0, 1, "", "SplitMode"], [0, 0, 1, "", "Tokenizer"], [0, 0, 1, "", "WordInfo"], [1, 3, 0, "-", "dictionary"], [2, 3, 0, "-", "morpheme"], [3, 3, 0, "-", "morphemelist"], [4, 3, 0, "-", "tokenizer"]], "sudachipy.Dictionary": [[0, 1, 1, "", "close"], [0, 1, 1, "", "create"], [0, 1, 1, "", "lookup"], [0, 1, 1, "", "pos_matcher"], [0, 1, 1, "", "pos_of"], [0, 1, 1, "", "pre_tokenizer"]], "sudachipy.Morpheme": [[0, 1, 1, "", "begin"], [0, 1, 1, "", "dictionary_form"], [0, 1, 1, "", "dictionary_id"], [0, 1, 1, "", "end"], [0, 1, 1, "", "get_word_info"], [0, 1, 1, "", "is_oov"], [0, 1, 1, "", "normalized_form"], [0, 1, 1, "", "part_of_speech"], [0, 1, 1, "", "part_of_speech_id"], [0, 1, 1, "", "raw_surface"], [0, 1, 1, "", "reading_form"], [0, 1, 1, "", "split"], [0, 1, 1, "", "surface"], [0, 1, 1, "", "synonym_group_ids"], [0, 1, 1, "", "word_id"]], "sudachipy.MorphemeList": [[0, 1, 1, "", "empty"], [0, 1, 1, "", "get_internal_cost"], [0, 1, 1, "", "size"]], "sudachipy.Tokenizer": [[0, 2, 1, "", "SplitMode"], [0, 1, 1, "", "tokenize"]], "sudachipy.WordInfo": [[0, 2, 1, "", "a_unit_split"], [0, 2, 1, "", "b_unit_split"], [0, 2, 1, "", "dictionary_form"], [0, 2, 1, "", "dictionary_form_word_id"], [0, 2, 1, "", "head_word_length"], [0, 1, 1, "", "length"], [0, 2, 1, "", "normalized_form"], [0, 2, 1, "", "pos_id"], [0, 2, 1, "", "reading_form"], [0, 2, 1, "", "surface"], [0, 2, 1, "", "synonym_group_ids"], [0, 2, 1, "", "word_structure"]], "sudachipy.config": [[0, 0, 1, "", "Config"]], "sudachipy.config.Config": [[0, 1, 1, "", "as_jsons"], [0, 2, 1, "", "projection"], [0, 2, 1, "", "system"], [0, 2, 1, "", "user"]], "sudachipy.dictionary": [[1, 0, 1, "", "Dictionary"]], "sudachipy.dictionary.Dictionary": [[1, 1, 1, "", "close"], [1, 1, 1, "", "create"], [1, 1, 1, "", "lookup"], [1, 1, 1, "", "pos_matcher"], [1, 1, 1, "", "pos_of"], [1, 1, 1, "", "pre_tokenizer"]], "sudachipy.morpheme": [[2, 0, 1, "", "Morpheme"]], "sudachipy.morpheme.Morpheme": [[2, 1, 1, "", "begin"], [2, 1, 1, "", "dictionary_form"], [2, 1, 1, "", "dictionary_id"], [2, 1, 1, "", "end"], [2, 1, 1, "", "get_word_info"], [2, 1, 1, "", "is_oov"], [2, 1, 1, "", "normalized_form"], [2, 1, 1, "", "part_of_speech"], [2, 1, 1, "", "part_of_speech_id"], [2, 1, 1, "", "raw_surface"], [2, 1, 1, "", "reading_form"], [2, 1, 1, "", "split"], [2, 1, 1, "", "surface"], [2, 1, 1, "", "synonym_group_ids"], [2, 1, 1, "", "word_id"]], "sudachipy.morphemelist": [[3, 0, 1, "", "MorphemeList"]], "sudachipy.morphemelist.MorphemeList": [[3, 1, 1, "", "empty"], [3, 1, 1, "", "get_internal_cost"], [3, 1, 1, "", "size"]], "sudachipy.tokenizer": [[4, 0, 1, "", "Tokenizer"]], "sudachipy.tokenizer.Tokenizer": [[4, 2, 1, "", "SplitMode"], [4, 1, 1, "", "tokenize"]]}, "objtypes": {"0": "py:class", "1": "py:method", "2": "py:attribute", "3": "py:module"}, "objnames": {"0": ["py", "class", "Python class"], "1": ["py", "method", "Python method"], "2": ["py", "attribute", "Python attribute"], "3": ["py", "module", "Python module"]}, "titleterms": {"sudachipi": [0, 1, 2, 3, 4, 5], "packag": [0, 1, 2, 3, 4], "config": 0, "dictionari": [0, 1], "splitmod": 0, "token": [0, 4], "morphem": [0, 2], "wordinfo": [0, 7], "note": [1, 2, 3, 4], "modul": [1, 2, 3, 4], "content": [1, 2, 3, 4], "morphemelist": 3, "welcom": 5, "document": 5, "topic": 5, "api": 5, "refer": 5, "indic": 5, "tabl": 5, "output": 6, "paramet": 6, "memori": 6, "reus": 6, "subset": 7, "wheel": 8, "statu": 8, "linux": 8, "window": 8, "maco": 8}, "envversion": {"sphinx.domains.c": 3, "sphinx.domains.changeset": 1, "sphinx.domains.citation": 1, "sphinx.domains.cpp": 9, "sphinx.domains.index": 1, "sphinx.domains.javascript": 3, "sphinx.domains.math": 2, "sphinx.domains.python": 4, "sphinx.domains.rst": 2, "sphinx.domains.std": 2, "sphinx.ext.viewcode": 1, "sphinx.ext.todo": 2, "sphinx": 60}, "alltitles": {"sudachipy package": [[0, "sudachipy-package"]], "config.Config": [[0, "config-config"]], "Dictionary": [[0, "dictionary"]], "SplitMode": [[0, "splitmode"]], "Tokenizer": [[0, "tokenizer"]], "Morpheme": [[0, "morpheme"]], "WordInfo": [[0, "wordinfo"]], "sudachipy.dictionary package": [[1, "sudachipy-dictionary-package"]], "Note": [[1, "note"], [2, "note"], [3, "note"], [4, "note"]], "Module contents": [[1, "module-sudachipy.dictionary"], [2, "module-sudachipy.morpheme"], [3, "module-sudachipy.morphemelist"], [4, "module-sudachipy.tokenizer"]], "sudachipy.morpheme package": [[2, "sudachipy-morpheme-package"]], "sudachipy.morphemelist package": [[3, "sudachipy-morphemelist-package"]], "sudachipy.tokenizer package": [[4, "sudachipy-tokenizer-package"]], "Welcome to SudachiPy documentation!": [[5, "welcome-to-sudachipy-documentation"]], "Topics": [[5, null]], "API Reference:": [[5, null]], "Indices and tables": [[5, "indices-and-tables"]], "Output Parameters and Memory Reuse": [[6, "output-parameters-and-memory-reuse"]], "WordInfo subsetting": [[7, "wordinfo-subsetting"]], "Wheel Status": [[8, "wheel-status"]], "Linux": [[8, "linux"]], "Windows": [[8, "windows"]], "macOS": [[8, "macos"]]}, "indexentries": {"config (class in sudachipy.config)": [[0, "sudachipy.config.Config"]], "dictionary (class in sudachipy)": [[0, "sudachipy.Dictionary"]], "morpheme (class in sudachipy)": [[0, "sudachipy.Morpheme"]], "morphemelist (class in sudachipy)": [[0, "sudachipy.MorphemeList"]], "splitmode (class in sudachipy)": [[0, "sudachipy.SplitMode"]], "splitmode (sudachipy.tokenizer attribute)": [[0, "sudachipy.Tokenizer.SplitMode"]], "tokenizer (class in sudachipy)": [[0, "sudachipy.Tokenizer"]], "wordinfo (class in sudachipy)": [[0, "sudachipy.WordInfo"]], "a_unit_split (sudachipy.wordinfo attribute)": [[0, "sudachipy.WordInfo.a_unit_split"]], "as_jsons() (sudachipy.config.config method)": [[0, "sudachipy.config.Config.as_jsons"]], "b_unit_split (sudachipy.wordinfo attribute)": [[0, "sudachipy.WordInfo.b_unit_split"]], "begin() (sudachipy.morpheme method)": [[0, "sudachipy.Morpheme.begin"]], "close() (sudachipy.dictionary method)": [[0, "sudachipy.Dictionary.close"]], "create() (sudachipy.dictionary method)": [[0, "sudachipy.Dictionary.create"]], "dictionary_form (sudachipy.wordinfo attribute)": [[0, "sudachipy.WordInfo.dictionary_form"]], "dictionary_form() (sudachipy.morpheme method)": [[0, "sudachipy.Morpheme.dictionary_form"]], "dictionary_form_word_id (sudachipy.wordinfo attribute)": [[0, "sudachipy.WordInfo.dictionary_form_word_id"]], "dictionary_id() (sudachipy.morpheme method)": [[0, "sudachipy.Morpheme.dictionary_id"]], "empty() (sudachipy.morphemelist method)": [[0, "sudachipy.MorphemeList.empty"]], "end() (sudachipy.morpheme method)": [[0, "sudachipy.Morpheme.end"]], "get_internal_cost() (sudachipy.morphemelist method)": [[0, "sudachipy.MorphemeList.get_internal_cost"]], "get_word_info() (sudachipy.morpheme method)": [[0, "sudachipy.Morpheme.get_word_info"]], "head_word_length (sudachipy.wordinfo attribute)": [[0, "sudachipy.WordInfo.head_word_length"]], "is_oov() (sudachipy.morpheme method)": [[0, "sudachipy.Morpheme.is_oov"]], "length() (sudachipy.wordinfo method)": [[0, "sudachipy.WordInfo.length"]], "lookup() (sudachipy.dictionary method)": [[0, "sudachipy.Dictionary.lookup"]], "normalized_form (sudachipy.wordinfo attribute)": [[0, "sudachipy.WordInfo.normalized_form"]], "normalized_form() (sudachipy.morpheme method)": [[0, "sudachipy.Morpheme.normalized_form"]], "part_of_speech() (sudachipy.morpheme method)": [[0, "sudachipy.Morpheme.part_of_speech"]], "part_of_speech_id() (sudachipy.morpheme method)": [[0, "sudachipy.Morpheme.part_of_speech_id"]], "pos_id (sudachipy.wordinfo attribute)": [[0, "sudachipy.WordInfo.pos_id"]], "pos_matcher() (sudachipy.dictionary method)": [[0, "sudachipy.Dictionary.pos_matcher"]], "pos_of() (sudachipy.dictionary method)": [[0, "sudachipy.Dictionary.pos_of"]], "pre_tokenizer() (sudachipy.dictionary method)": [[0, "sudachipy.Dictionary.pre_tokenizer"]], "projection (sudachipy.config.config attribute)": [[0, "sudachipy.config.Config.projection"]], "raw_surface() (sudachipy.morpheme method)": [[0, "sudachipy.Morpheme.raw_surface"]], "reading_form (sudachipy.wordinfo attribute)": [[0, "sudachipy.WordInfo.reading_form"]], "reading_form() (sudachipy.morpheme method)": [[0, "sudachipy.Morpheme.reading_form"]], "size() (sudachipy.morphemelist method)": [[0, "sudachipy.MorphemeList.size"]], "split() (sudachipy.morpheme method)": [[0, "sudachipy.Morpheme.split"]], "surface (sudachipy.wordinfo attribute)": [[0, "sudachipy.WordInfo.surface"]], "surface() (sudachipy.morpheme method)": [[0, "sudachipy.Morpheme.surface"]], "synonym_group_ids (sudachipy.wordinfo attribute)": [[0, "sudachipy.WordInfo.synonym_group_ids"]], "synonym_group_ids() (sudachipy.morpheme method)": [[0, "sudachipy.Morpheme.synonym_group_ids"]], "system (sudachipy.config.config attribute)": [[0, "sudachipy.config.Config.system"]], "tokenize() (sudachipy.tokenizer method)": [[0, "sudachipy.Tokenizer.tokenize"]], "user (sudachipy.config.config attribute)": [[0, "sudachipy.config.Config.user"]], "word_id() (sudachipy.morpheme method)": [[0, "sudachipy.Morpheme.word_id"]], "word_structure (sudachipy.wordinfo attribute)": [[0, "sudachipy.WordInfo.word_structure"]], "dictionary (class in sudachipy.dictionary)": [[1, "sudachipy.dictionary.Dictionary"]], "close() (sudachipy.dictionary.dictionary method)": [[1, "sudachipy.dictionary.Dictionary.close"]], "create() (sudachipy.dictionary.dictionary method)": [[1, "sudachipy.dictionary.Dictionary.create"]], "lookup() (sudachipy.dictionary.dictionary method)": [[1, "sudachipy.dictionary.Dictionary.lookup"]], "module": [[1, "module-sudachipy.dictionary"], [2, "module-sudachipy.morpheme"], [3, "module-sudachipy.morphemelist"], [4, "module-sudachipy.tokenizer"]], "pos_matcher() (sudachipy.dictionary.dictionary method)": [[1, "sudachipy.dictionary.Dictionary.pos_matcher"]], "pos_of() (sudachipy.dictionary.dictionary method)": [[1, "sudachipy.dictionary.Dictionary.pos_of"]], "pre_tokenizer() (sudachipy.dictionary.dictionary method)": [[1, "sudachipy.dictionary.Dictionary.pre_tokenizer"]], "sudachipy.dictionary": [[1, "module-sudachipy.dictionary"]], "morpheme (class in sudachipy.morpheme)": [[2, "sudachipy.morpheme.Morpheme"]], "begin() (sudachipy.morpheme.morpheme method)": [[2, "sudachipy.morpheme.Morpheme.begin"]], "dictionary_form() (sudachipy.morpheme.morpheme method)": [[2, "sudachipy.morpheme.Morpheme.dictionary_form"]], "dictionary_id() (sudachipy.morpheme.morpheme method)": [[2, "sudachipy.morpheme.Morpheme.dictionary_id"]], "end() (sudachipy.morpheme.morpheme method)": [[2, "sudachipy.morpheme.Morpheme.end"]], "get_word_info() (sudachipy.morpheme.morpheme method)": [[2, "sudachipy.morpheme.Morpheme.get_word_info"]], "is_oov() (sudachipy.morpheme.morpheme method)": [[2, "sudachipy.morpheme.Morpheme.is_oov"]], "normalized_form() (sudachipy.morpheme.morpheme method)": [[2, "sudachipy.morpheme.Morpheme.normalized_form"]], "part_of_speech() (sudachipy.morpheme.morpheme method)": [[2, "sudachipy.morpheme.Morpheme.part_of_speech"]], "part_of_speech_id() (sudachipy.morpheme.morpheme method)": [[2, "sudachipy.morpheme.Morpheme.part_of_speech_id"]], "raw_surface() (sudachipy.morpheme.morpheme method)": [[2, "sudachipy.morpheme.Morpheme.raw_surface"]], "reading_form() (sudachipy.morpheme.morpheme method)": [[2, "sudachipy.morpheme.Morpheme.reading_form"]], "split() (sudachipy.morpheme.morpheme method)": [[2, "sudachipy.morpheme.Morpheme.split"]], "sudachipy.morpheme": [[2, "module-sudachipy.morpheme"]], "surface() (sudachipy.morpheme.morpheme method)": [[2, "sudachipy.morpheme.Morpheme.surface"]], "synonym_group_ids() (sudachipy.morpheme.morpheme method)": [[2, "sudachipy.morpheme.Morpheme.synonym_group_ids"]], "word_id() (sudachipy.morpheme.morpheme method)": [[2, "sudachipy.morpheme.Morpheme.word_id"]], "morphemelist (class in sudachipy.morphemelist)": [[3, "sudachipy.morphemelist.MorphemeList"]], "empty() (sudachipy.morphemelist.morphemelist method)": [[3, "sudachipy.morphemelist.MorphemeList.empty"]], "get_internal_cost() (sudachipy.morphemelist.morphemelist method)": [[3, "sudachipy.morphemelist.MorphemeList.get_internal_cost"]], "size() (sudachipy.morphemelist.morphemelist method)": [[3, "sudachipy.morphemelist.MorphemeList.size"]], "sudachipy.morphemelist": [[3, "module-sudachipy.morphemelist"]], "splitmode (sudachipy.tokenizer.tokenizer attribute)": [[4, "sudachipy.tokenizer.Tokenizer.SplitMode"]], "tokenizer (class in sudachipy.tokenizer)": [[4, "sudachipy.tokenizer.Tokenizer"]], "sudachipy.tokenizer": [[4, "module-sudachipy.tokenizer"]], "tokenize() (sudachipy.tokenizer.tokenizer method)": [[4, "sudachipy.tokenizer.Tokenizer.tokenize"]]}}) \ No newline at end of file