{ "info": { "author": "Li Ding", "author_email": "lidingpku@gmail.com", "bugtrack_url": null, "classifiers": [ "Development Status :: 3 - Alpha", "License :: OSI Approved :: Apache Software License", "Programming Language :: Python :: 2.7", "Topic :: Text Processing" ], "description": "cdata\n-------------\n\n\"see data\", see data, handy snippets for conversion, cleaning and integration.\n\ninstall\n-------------\n pip install cdata\n\n\njson data manipulation\n-------------\n\n* json (and json stream) file IO, e.g. items2file(...)\n* json data access, e.g. json_get(...), any2utf8, json_dict_copy\n* json array statistics, e.g. stat(...)\n\n.. code-block:: python\n\n from cdata.core import any2utf8\n the_input = {\"hello\": u\"\u4e16\u754c\"}\n the_output = any2utf8(the_input)\n logging.info((the_input, the_output))\n\n\n.. code-block:: python\n property_list = [\n { \"name\":\"name\", \"alternateName\": [\"name\",\"title\"]},\n { \"name\":\"birthDate\", \"alternateName\": [\"dob\",\"dateOfBirth\"] },\n { \"name\":\"description\" }\n ]\n json_object = {\"dob\":\"2010-01-01\",\"title\":\"John\",\"interests\":\"data\",\"description\":\"a person\"}\n ret = json_dict_copy(json_object, property_list)\n\n\ntable data manipulation\n-------------\n\n* json array to/from excel\n\n.. code-block:: python\n\n import json\n from cdata.table import excel2json,json2excel\n filename = \"test.xls\"\n items = [{\"first\":\"hello\", \"last\":\"world\" }]\n json2excel(items, [\"first\",\"last\"], filename)\n ret = excel2json(filename)\n print json.dumps(ret)\n\n\n\nJSON data from reading a single sheet excel file\n\n.. code-block:: json\n\n {\n \"fields\": {\n \"00\": [\n \"name\",\n \"\u5e74\u9f84\",\n \"notes\"\n ]\n },\n \"data\": {\n \"00\": [\n {\n \"notes\": \"\",\n \"\u5e74\u9f84\": 18.0,\n \"name\": \"\u5f20\u4e09\"\n },\n {\n \"notes\": \"this is li si\",\n \"\u5e74\u9f84\": 18.0,\n \"name\": \"\u674e\u56db\"\n }\n ]\n }\n }\n\nweb stuff\n-------------\n\n* url domain extraction\n\nentity manipulation\n-------------\n\n* entity.SimpleEntity.ner()\n\n.. code-block:: python\n\n from cdata.entity import SimpleEntity\n entity_list = [{\"@id\":\"1\",\"name\":u\"\u5f20\u4e09\"},{\"@id\":\"2\",\"name\":u\"\u674e\u56db\"}]\n ner = SimpleEntity(entity_list)\n sentence = \"\u5f20\u4e09\u7ed9\u4e86\u674e\u56db\u4e00\u4e2a\u82f9\u679c\"\n ret = ner.ner(sentence)\n logging.info(json.dumps(ret, ensure_ascii=False, indent=4))\n \"\"\"\n [{\n \"text\": \"\u5f20\u4e09\",\n \"entities\": [\n {\n \"@id\": \"1\",\n \"name\": \"\u5f20\u4e09\"\n }\n ],\n \"index\": 0\n },\n {\n \"text\": \"\u674e\u56db\",\n \"entities\": [\n {\n \"@id\": \"2\",\n \"name\": \"\u674e\u56db\"\n }\n ],\n \"index\": 4\n }]\n \"\"\"\n\n* region.RegionEntity.guess_all()\n\n.. code-block:: python\n\n from cdata.region import RegionEntity\n addresses = [\"\u5317\u4eac\u6d77\u6dc0\u533a\u961c\u6210\u8def52\u53f7\uff08\u5b9a\u6167\u5bfa\uff09\", \"\u5317\u4eac\u5927\u5b66\u80bf\u7624\u533b\u9662\"]\n\n city_data = RegionEntity()\n result = city_data.guess_all(addresses)\n logging.info(json.dumps(result, ensure_ascii=False))\n \"\"\"\n {\"province\": \"\u5317\u4eac\u5e02\",\n \"city\": \"\u5e02\u8f96\u533a\",\n \"name\": \"\u6d77\u6dc0\u533a\",\n \"district\": \"\u6d77\u6dc0\u533a\",\n \"cityid\": \"110108\",\n \"type\": \"district\"}\n \"\"\"\n\nwikification\n-------------\n\n* \u901a\u8fc7wikidata\u641c\u7d22\uff0c\u5b9a\u4f4d\u5bf9\u5e94\u5b9e\u4f53\uff0c\u67e5\u627e\u5b9e\u4f53\u4e2d\u6587\u540d\uff0c\u522b\u540d\u7b49\u5c5e\u6027\u3002wikidata_search (item/property) and wikidata_get\n\n.. code-block:: python\n\n query = u\"\u5c45\u91cc\u592b\u4eba\"\n ret = wikidata_search(query, lang=\"zh\")\n logging.info(ret)\n\n nodeid = ret[\"itemList\"][0][\"identifier\"]\n ret = wikidata_get(nodeid)\n lable_zh = ret[\"entities\"][nodeid][\"labels\"][\"zh\"][\"value\"]\n logging.info(lable_zh)\n\n\nmisc\n-------------\n\n* support simple cli function using argparse\n\n\nnotes\n-------------\nrelease package using https://github.com/pypa/twine", "description_content_type": null, "docs_url": null, "download_url": "", "downloads": { "last_day": -1, "last_month": -1, "last_week": -1 }, "home_page": "http://github.com/cnschema/cdata", "keywords": "", "license": "Apache 2.0", "maintainer": "", "maintainer_email": "", "name": "cdata", "package_url": "https://pypi.org/project/cdata/", "platform": "", "project_url": "https://pypi.org/project/cdata/", "project_urls": { "Homepage": "http://github.com/cnschema/cdata" }, "release_url": "https://pypi.org/project/cdata/0.1.9/", "requires_dist": null, "requires_python": "", "summary": "see data, handy snippets for conversion, and ETL.", "version": "0.1.9" }, "last_serial": 3175524, "releases": { "0.0.1": [ { "comment_text": "", "digests": { "md5": "f78f69c0572a987c07a1ba8614ee5279", "sha256": "a18c5149f16cf9c3bf8eb962fcfad7e789c8856896275ff1d4ab6ca87159a9c5" }, "downloads": -1, "filename": "cdata-0.0.1-py2-none-any.whl", "has_sig": false, "md5_digest": "f78f69c0572a987c07a1ba8614ee5279", "packagetype": "bdist_wheel", "python_version": "py2", "requires_python": null, "size": 17356, "upload_time": "2017-06-22T23:53:36", "url": "https://files.pythonhosted.org/packages/ad/5d/79408fd2474c15177e4419a2db1281dd74f4283989d9e9f40fe4725e085f/cdata-0.0.1-py2-none-any.whl" }, { "comment_text": "", "digests": { "md5": "9c26dc3b33be3b71aa1144df3c804f57", "sha256": "790b5612f99131f30708659328a4a8c005d727fee9388a8c01922a5f1c6af9c8" }, "downloads": -1, "filename": "cdata-0.0.1.tar.gz", "has_sig": false, "md5_digest": "9c26dc3b33be3b71aa1144df3c804f57", "packagetype": "sdist", "python_version": "source", "requires_python": null, "size": 5163, "upload_time": "2017-06-19T23:35:20", "url": "https://files.pythonhosted.org/packages/f9/32/2c030194240353a5082966e9e5b535886e5866b3401110268db26d09e0ee/cdata-0.0.1.tar.gz" } ], "0.1.2": [ { "comment_text": "", "digests": { "md5": "98df6aa4a066ec42809487d603f2dde3", "sha256": "19a1bf902da28fa43c95914edbb45694440cd2666298c17fd72d81048a941453" }, "downloads": -1, "filename": "cdata-0.1.2-py2-none-any.whl", "has_sig": false, "md5_digest": "98df6aa4a066ec42809487d603f2dde3", "packagetype": "bdist_wheel", "python_version": "py2", "requires_python": null, "size": 17364, "upload_time": "2017-06-22T23:53:38", "url": "https://files.pythonhosted.org/packages/10/2f/68cf15545040afda613eae18e328b509595b810df392f7b1381d022ae809/cdata-0.1.2-py2-none-any.whl" } ], "0.1.4": [ { "comment_text": "", "digests": { "md5": "3b21b141ff709260aad07b63be7a4f55", "sha256": "e5a6829d77893f85e2aab3dadb2191662ac41f9832b8b84e9dfa05b34d13eac9" }, "downloads": -1, "filename": "cdata-0.1.4.tar.gz", "has_sig": false, "md5_digest": "3b21b141ff709260aad07b63be7a4f55", "packagetype": "sdist", "python_version": "source", "requires_python": null, "size": 51715, "upload_time": "2017-07-18T12:51:37", "url": "https://files.pythonhosted.org/packages/76/1a/90712e4384402d89d2058e63e52bf94f8a47dd8b52aaface33d90e2e51c7/cdata-0.1.4.tar.gz" } ], "0.1.6": [ { "comment_text": "", "digests": { "md5": "508fdbbea0a1864b2de2c3bfe2448264", "sha256": "90052a2d747611cacf7006d7b6c0091f908bfc84d38f197ee61753d3533e041d" }, "downloads": -1, "filename": "cdata-0.1.6.tar.gz", "has_sig": false, "md5_digest": "508fdbbea0a1864b2de2c3bfe2448264", "packagetype": "sdist", "python_version": "source", "requires_python": null, "size": 54412, "upload_time": "2017-07-20T08:57:26", "url": "https://files.pythonhosted.org/packages/c5/09/3c195830ab66c19e19ca1e97dde9cb0a092bb8be106aa4acf314cf0baef3/cdata-0.1.6.tar.gz" } ], "0.1.7": [ { "comment_text": "", "digests": { "md5": "4a79836eac598092f9dcfedcc486517f", "sha256": "92cfec06a1a33deff9aa84a5028160d0c898bb54550d74b0cf5b4e15ed2886df" }, "downloads": -1, "filename": "cdata-0.1.7.tar.gz", "has_sig": false, "md5_digest": "4a79836eac598092f9dcfedcc486517f", "packagetype": "sdist", "python_version": "source", "requires_python": null, "size": 54601, "upload_time": "2017-07-20T10:21:14", "url": "https://files.pythonhosted.org/packages/22/ec/3f96c9f45c7478d06c5fb5c8c7701a1733172b1d2875421844f25469be76/cdata-0.1.7.tar.gz" } ], "0.1.8": [ { "comment_text": "", "digests": { "md5": "83b3422470df851e390269461e66a024", "sha256": "518ee1b0967f8bdf69c92089dd7f7dd7d2cb18d504fa0cd4ddafcbd8a1223464" }, "downloads": -1, "filename": "cdata-0.1.8.tar.gz", "has_sig": false, "md5_digest": "83b3422470df851e390269461e66a024", "packagetype": "sdist", "python_version": "source", "requires_python": null, "size": 53738, "upload_time": "2017-08-17T00:53:02", "url": "https://files.pythonhosted.org/packages/34/24/9888c913ab0787fcdfce06a4bba85971289628629e42a7ee7d11fd742c0e/cdata-0.1.8.tar.gz" } ], "0.1.9": [ { "comment_text": "", "digests": { "md5": "8c7572f26360039261bb75ce30a8f448", "sha256": "4e7699ba6a38c780a18bd47f0d0637e255376df8f947f6ea02e0e45ffe4362c6" }, "downloads": -1, "filename": "cdata-0.1.9.tar.gz", "has_sig": false, "md5_digest": "8c7572f26360039261bb75ce30a8f448", "packagetype": "sdist", "python_version": "source", "requires_python": null, "size": 54538, "upload_time": "2017-09-15T07:20:42", "url": "https://files.pythonhosted.org/packages/76/ca/5e861dd3a4704eecad3576826d447ec448aa4190ebf17fba5fbe3949e68c/cdata-0.1.9.tar.gz" } ] }, "urls": [ { "comment_text": "", "digests": { "md5": "8c7572f26360039261bb75ce30a8f448", "sha256": "4e7699ba6a38c780a18bd47f0d0637e255376df8f947f6ea02e0e45ffe4362c6" }, "downloads": -1, "filename": "cdata-0.1.9.tar.gz", "has_sig": false, "md5_digest": "8c7572f26360039261bb75ce30a8f448", "packagetype": "sdist", "python_version": "source", "requires_python": null, "size": 54538, "upload_time": "2017-09-15T07:20:42", "url": "https://files.pythonhosted.org/packages/76/ca/5e861dd3a4704eecad3576826d447ec448aa4190ebf17fba5fbe3949e68c/cdata-0.1.9.tar.gz" } ] }