{"id":37323,"name":"pinyintokenizer","description":"pinyintokenizer, 拼音分词器，将连续的拼音切分为单字拼音列表。","url":"https://github.com/shibing624/pinyin-tokenizer","last_synced_at":"2025-09-05T07:23:11.342Z","repository":{"id":65122306,"uuid":"582262114","full_name":"shibing624/pinyin-tokenizer","owner":"shibing624","description":"pinyintokenizer, 拼音分词器，将连续的拼音切分为单字拼音列表。","archived":false,"fork":false,"pushed_at":"2025-02-05T08:05:06.000Z","size":62,"stargazers_count":31,"open_issues_count":0,"forks_count":2,"subscribers_count":2,"default_branch":"main","last_synced_at":"2025-08-19T05:26:14.384Z","etag":null,"topics":["nlp","pinyin","pinyin-analysis","pinyin4j","tokenizer","trie-tree"],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"apache-2.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/shibing624.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":"CONTRIBUTING.md","funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":"CITATION.cff","codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null}},"created_at":"2022-12-26T09:00:48.000Z","updated_at":"2025-08-07T12:28:00.000Z","dependencies_parsed_at":"2025-04-12T04:23:57.781Z","dependency_job_id":"1b625dc2-e90d-4ed0-8aeb-e297d7cbc4d7","html_url":"https://github.com/shibing624/pinyin-tokenizer","commit_stats":{"total_commits":7,"total_committers":1,"mean_commits":7.0,"dds":0.0,"last_synced_commit":"2c68a2486204b7e19e66604ee39764e8e2cdd624"},"previous_names":[],"tags_count":2,"template":false,"template_full_name":null,"purl":"pkg:github/shibing624/pinyin-tokenizer","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/shibing624%2Fpinyin-tokenizer","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/shibing624%2Fpinyin-tokenizer/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/shibing624%2Fpinyin-tokenizer/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/shibing624%2Fpinyin-tokenizer/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/shibing624","download_url":"https://codeload.github.com/shibing624/pinyin-tokenizer/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/shibing624%2Fpinyin-tokenizer/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":273724971,"owners_count":25156617,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","status":"online","status_checked_at":"2025-09-05T02:00:09.113Z","response_time":402,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"owner":{"login":"shibing624","name":"xuming","uuid":"10249622","kind":"user","description":"Senior Researcher, Machine Learning Developer, Advertising Risk Control.","email":"","website":"https://blog.csdn.net/mingzai624","location":"Beijing, China","twitter":null,"company":"@tencent","icon_url":"https://avatars.githubusercontent.com/u/10249622?u=39133b98c78fe7cbaf0458be30352f1c5b1197c4\u0026v=4","repositories_count":32,"last_synced_at":"2023-02-26T09:45:33.381Z","metadata":{"has_sponsors_listing":false},"html_url":"https://github.com/shibing624","funding_links":[],"total_stars":null,"followers":null,"following":null,"created_at":"2022-11-09T21:45:36.732Z","updated_at":"2023-02-26T09:45:33.417Z","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/shibing624","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/shibing624/repositories"},"packages":[{"id":5747784,"name":"pinyintokenizer","ecosystem":"pypi","description":"Pinyin Tokenizer, chinese pinyin tokenizer","homepage":"https://github.com/shibing624/pinyin-tokenizer","licenses":"Apache 2.0","normalized_licenses":["Apache-2.0"],"repository_url":"https://github.com/shibing624/pinyin-tokenizer","keywords_array":["pinyin-tokenizer","pinyin","pinyintokenizer","tokenizer"],"namespace":null,"versions_count":3,"first_release_published_at":"2022-12-26T09:52:27.000Z","latest_release_published_at":"2025-01-28T09:07:39.000Z","latest_release_number":"0.0.3","last_synced_at":"2025-08-19T05:17:26.065Z","created_at":"2022-12-26T09:57:50.798Z","updated_at":"2025-08-19T05:38:43.774Z","registry_url":"https://pypi.org/project/pinyintokenizer/","install_command":"pip install pinyintokenizer --index-url https://pypi.org/simple","documentation_url":"https://pinyintokenizer.readthedocs.io/","metadata":{"funding":null,"documentation":null,"classifiers":["Intended Audience :: Science/Research","License :: OSI Approved :: Apache Software License","Operating System :: OS Independent","Programming Language :: Python","Programming Language :: Python :: 2.7","Programming Language :: Python :: 3","Topic :: Scientific/Engineering :: Artificial Intelligence","Topic :: Text Processing :: Linguistic"],"normalized_name":"pinyintokenizer","project_status":null},"repo_metadata":{"id":65122306,"uuid":"582262114","full_name":"shibing624/pinyin-tokenizer","owner":"shibing624","description":"pinyintokenizer, 拼音分词器，将连续的拼音切分为单字拼音列表。","archived":false,"fork":false,"pushed_at":"2025-02-05T08:05:06.000Z","size":62,"stargazers_count":30,"open_issues_count":0,"forks_count":2,"subscribers_count":2,"default_branch":"main","last_synced_at":"2025-07-05T13:23:09.690Z","etag":null,"topics":["nlp","pinyin","pinyin-analysis","pinyin4j","tokenizer","trie-tree"],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"apache-2.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/shibing624.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":"CONTRIBUTING.md","funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":"CITATION.cff","codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null}},"created_at":"2022-12-26T09:00:48.000Z","updated_at":"2025-04-13T09:54:02.000Z","dependencies_parsed_at":"2025-04-12T04:23:57.781Z","dependency_job_id":"1b625dc2-e90d-4ed0-8aeb-e297d7cbc4d7","html_url":"https://github.com/shibing624/pinyin-tokenizer","commit_stats":{"total_commits":7,"total_committers":1,"mean_commits":7.0,"dds":0.0,"last_synced_commit":"2c68a2486204b7e19e66604ee39764e8e2cdd624"},"previous_names":[],"tags_count":2,"template":false,"template_full_name":null,"purl":"pkg:github/shibing624/pinyin-tokenizer","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/shibing624%2Fpinyin-tokenizer","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/shibing624%2Fpinyin-tokenizer/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/shibing624%2Fpinyin-tokenizer/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/shibing624%2Fpinyin-tokenizer/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/shibing624","download_url":"https://codeload.github.com/shibing624/pinyin-tokenizer/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/shibing624%2Fpinyin-tokenizer/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":271103202,"owners_count":24699646,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","status":"online","status_checked_at":"2025-08-19T02:00:09.176Z","response_time":63,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"},"owner_record":{"login":"shibing624","name":"xuming","uuid":"10249622","kind":"user","description":"Senior Researcher, Machine Learning Developer, Advertising Risk Control.","email":"","website":"https://blog.csdn.net/mingzai624","location":"Beijing, China","twitter":null,"company":"@tencent","icon_url":"https://avatars.githubusercontent.com/u/10249622?u=39133b98c78fe7cbaf0458be30352f1c5b1197c4\u0026v=4","repositories_count":32,"last_synced_at":"2023-02-26T09:45:33.381Z","metadata":{"has_sponsors_listing":false},"html_url":"https://github.com/shibing624","funding_links":[],"total_stars":null,"followers":null,"following":null,"created_at":"2022-11-09T21:45:36.732Z","updated_at":"2023-02-26T09:45:33.417Z","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/shibing624","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/shibing624/repositories"},"tags":[{"name":"0.0.2","sha":"2c68a2486204b7e19e66604ee39764e8e2cdd624","kind":"commit","published_at":"2022-12-28T06:22:29.000Z","download_url":"https://codeload.github.com/shibing624/pinyin-tokenizer/tar.gz/0.0.2","html_url":"https://github.com/shibing624/pinyin-tokenizer/releases/tag/0.0.2","dependencies_parsed_at":null,"dependency_job_id":null,"purl":"pkg:github/shibing624/pinyin-tokenizer@0.0.2","tag_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/shibing624%2Fpinyin-tokenizer/tags/0.0.2","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/shibing624%2Fpinyin-tokenizer/tags/0.0.2/manifests"},{"name":"0.0.1","sha":"bd45fa2fa88101210d20b8b0fa4009f57156a82a","kind":"commit","published_at":"2022-12-26T09:50:49.000Z","download_url":"https://codeload.github.com/shibing624/pinyin-tokenizer/tar.gz/0.0.1","html_url":"https://github.com/shibing624/pinyin-tokenizer/releases/tag/0.0.1","dependencies_parsed_at":null,"dependency_job_id":null,"purl":"pkg:github/shibing624/pinyin-tokenizer@0.0.1","tag_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/shibing624%2Fpinyin-tokenizer/tags/0.0.1","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/shibing624%2Fpinyin-tokenizer/tags/0.0.1/manifests"}]},"repo_metadata_updated_at":"2025-08-19T05:38:43.773Z","dependent_packages_count":0,"downloads":1035,"downloads_period":"last-month","dependent_repos_count":0,"rankings":{"downloads":49.85775821726535,"dependent_repos_count":30.61104109666564,"dependent_packages_count":6.633233862033089,"stargazers_count":21.76136029723853,"forks_count":23.200755720688072,"average":26.412829838778134},"purl":"pkg:pypi/pinyintokenizer","advisories":[],"docker_usage_url":"https://docker.ecosyste.ms/usage/pypi/pinyintokenizer","docker_dependents_count":null,"docker_downloads_count":null,"usage_url":"https://repos.ecosyste.ms/usage/pypi/pinyintokenizer","dependent_repositories_url":"https://repos.ecosyste.ms/api/v1/usage/pypi/pinyintokenizer/dependencies","status":null,"funding_links":[],"critical":null,"issue_metadata":{"last_synced_at":"2025-07-17T09:41:31.351Z","issues_count":2,"pull_requests_count":0,"avg_time_to_close_issue":205942.5,"avg_time_to_close_pull_request":null,"issues_closed_count":2,"pull_requests_closed_count":0,"pull_request_authors_count":0,"issue_authors_count":2,"avg_comments_per_issue":4.0,"avg_comments_per_pull_request":null,"merged_pull_requests_count":0,"bot_issues_count":0,"bot_pull_requests_count":0,"past_year_issues_count":1,"past_year_pull_requests_count":0,"past_year_avg_time_to_close_issue":410635.0,"past_year_avg_time_to_close_pull_request":null,"past_year_issues_closed_count":1,"past_year_pull_requests_closed_count":0,"past_year_pull_request_authors_count":0,"past_year_issue_authors_count":1,"past_year_avg_comments_per_issue":5.0,"past_year_avg_comments_per_pull_request":null,"past_year_bot_issues_count":0,"past_year_bot_pull_requests_count":0,"past_year_merged_pull_requests_count":0,"issues_url":"https://issues.ecosyste.ms/api/v1/hosts/GitHub/repositories/shibing624%2Fpinyin-tokenizer/issues","maintainers":[],"active_maintainers":[]},"versions_url":"https://packages.ecosyste.ms/api/v1/registries/pypi.org/packages/pinyintokenizer/versions","version_numbers_url":"https://packages.ecosyste.ms/api/v1/registries/pypi.org/packages/pinyintokenizer/version_numbers","dependent_packages_url":"https://packages.ecosyste.ms/api/v1/registries/pypi.org/packages/pinyintokenizer/dependent_packages","related_packages_url":"https://packages.ecosyste.ms/api/v1/registries/pypi.org/packages/pinyintokenizer/related_packages","maintainers":[{"uuid":"shibing624","login":"shibing624","name":null,"email":null,"url":null,"packages_count":32,"html_url":"https://pypi.org/user/shibing624/","role":null,"created_at":"2023-02-07T16:45:48.827Z","updated_at":"2023-02-07T16:45:48.827Z","packages_url":"https://packages.ecosyste.ms/api/v1/registries/pypi.org/maintainers/shibing624/packages"}],"registry":{"name":"pypi.org","url":"https://pypi.org","ecosystem":"pypi","default":true,"packages_count":725017,"maintainers_count":308331,"namespaces_count":0,"keywords_count":238006,"github":"pypi","metadata":{"funded_packages_count":50519},"icon_url":"https://github.com/pypi.png","created_at":"2022-04-04T15:19:23.364Z","updated_at":"2025-09-05T05:40:58.860Z","packages_url":"https://packages.ecosyste.ms/api/v1/registries/pypi.org/packages","maintainers_url":"https://packages.ecosyste.ms/api/v1/registries/pypi.org/maintainers","namespaces_url":"https://packages.ecosyste.ms/api/v1/registries/pypi.org/namespaces"}}],"commits":{"id":696882,"full_name":"shibing624/pinyin-tokenizer","default_branch":"main","committers":[{"name":"shibing624","email":"shibing624@126.com","count":7}],"total_commits":7,"total_committers":1,"total_bot_commits":0,"total_bot_committers":0,"mean_commits":7.0,"dds":0.0,"past_year_committers":null,"past_year_total_commits":null,"past_year_total_committers":null,"past_year_total_bot_commits":null,"past_year_total_bot_committers":null,"past_year_mean_commits":null,"past_year_dds":null,"last_synced_at":"2023-03-20T12:43:31.815Z","last_synced_commit":"2c68a2486204b7e19e66604ee39764e8e2cdd624","created_at":"2023-03-09T11:43:50.288Z","updated_at":"2023-09-19T17:40:58.956Z","commits_url":"https://commits.ecosyste.ms/api/v1/hosts/GitHub/repositories/shibing624%2Fpinyin-tokenizer/commits","host":{"name":"GitHub","url":"https://github.com","kind":"github","last_synced_at":"2025-09-05T00:00:10.343Z","repositories_count":5480019,"commits_count":853389012,"contributors_count":31098138,"owners_count":906558,"icon_url":"https://github.com/github.png","host_url":"https://commits.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://commits.ecosyste.ms/api/v1/hosts/GitHub/repositories"}},"issues_stats":{"full_name":"shibing624/pinyin-tokenizer","html_url":"https://github.com/shibing624/pinyin-tokenizer","last_synced_at":"2025-08-19T05:17:26.932Z","status":"error","issues_count":2,"pull_requests_count":0,"avg_time_to_close_issue":205942.5,"avg_time_to_close_pull_request":null,"issues_closed_count":2,"pull_requests_closed_count":0,"pull_request_authors_count":0,"issue_authors_count":2,"avg_comments_per_issue":4.0,"avg_comments_per_pull_request":null,"merged_pull_requests_count":0,"bot_issues_count":0,"bot_pull_requests_count":0,"past_year_issues_count":1,"past_year_pull_requests_count":0,"past_year_avg_time_to_close_issue":410635.0,"past_year_avg_time_to_close_pull_request":null,"past_year_issues_closed_count":1,"past_year_pull_requests_closed_count":0,"past_year_pull_request_authors_count":0,"past_year_issue_authors_count":1,"past_year_avg_comments_per_issue":5.0,"past_year_avg_comments_per_pull_request":null,"past_year_bot_issues_count":0,"past_year_bot_pull_requests_count":0,"past_year_merged_pull_requests_count":0,"created_at":"2023-05-15T05:52:12.330Z","updated_at":"2025-08-19T05:17:26.933Z","repository_url":"https://issues.ecosyste.ms/api/v1/hosts/GitHub/repositories/shibing624%2Fpinyin-tokenizer","issues_url":"https://issues.ecosyste.ms/api/v1/hosts/GitHub/repositories/shibing624%2Fpinyin-tokenizer/issues","issue_labels_count":{},"pull_request_labels_count":{},"issue_author_associations_count":{"NONE":2},"pull_request_author_associations_count":{},"issue_authors":{"Vange95":1,"demoliisher":1},"pull_request_authors":{},"host":{"name":"GitHub","url":"https://github.com","kind":"github","last_synced_at":"2025-08-31T00:00:11.523Z","repositories_count":8445427,"issues_count":20722327,"pull_requests_count":52188437,"authors_count":7941772,"icon_url":"https://github.com/github.png","host_url":"https://issues.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://issues.ecosyste.ms/api/v1/hosts/GitHub/repositories","owners_url":"https://issues.ecosyste.ms/api/v1/hosts/GitHub/owners","authors_url":"https://issues.ecosyste.ms/api/v1/hosts/GitHub/authors"},"past_year_issue_labels_count":{},"past_year_pull_request_labels_count":{},"past_year_issue_author_associations_count":{"NONE":1},"past_year_pull_request_author_associations_count":{},"past_year_issue_authors":{"demoliisher":1},"past_year_pull_request_authors":{},"maintainers":[],"active_maintainers":[]},"events":{"total":{"IssuesEvent":2,"WatchEvent":4,"IssueCommentEvent":6,"PushEvent":2},"last_year":{"IssuesEvent":2,"WatchEvent":4,"IssueCommentEvent":6,"PushEvent":2}},"keywords":["nlp","pinyin","pinyin-analysis","pinyin4j","tokenizer","trie-tree"],"dependencies":[{"ecosystem":"pypi","filepath":"requirements.txt","sha":null,"kind":"manifest","created_at":"2023-01-12T08:15:35.633Z","updated_at":"2023-01-12T08:15:35.633Z","repository_link":"https://github.com/shibing624/pinyin-tokenizer/blob/main/requirements.txt","dependencies":[{"id":6874399424,"package_name":"six","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false}]},{"ecosystem":"pypi","filepath":"setup.py","sha":null,"kind":"manifest","created_at":"2023-01-12T08:15:35.763Z","updated_at":"2023-01-12T08:15:35.763Z","repository_link":"https://github.com/shibing624/pinyin-tokenizer/blob/main/setup.py","dependencies":[{"id":6874399568,"package_name":"six","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false}]}],"score":10.377109627304574,"created_at":"2025-09-04T15:51:11.016Z","updated_at":"2025-10-07T08:15:21.906Z","avatar_url":"https://github.com/shibing624.png","language":"Python","category":null,"sub_category":null,"monthly_downloads":1035,"funding_links":[],"readme_doi_urls":[],"works":{},"citation_counts":{},"total_citations":0,"keywords_from_contributors":[],"project_url":"https://science.ecosyste.ms/api/v1/projects/37323","html_url":"https://science.ecosyste.ms/projects/37323","bibtex_url":"https://science.ecosyste.ms/projects/37323/export.bibtex","apalike_url":"https://science.ecosyste.ms/projects/37323/export.apalike"}