update lang/zh (#4103)

* update lang/zh

* update lang/zh

.github/contributors/phiedulxp.md

@@ -0,0 +1,106 @@
+# spaCy contributor agreement
+
+This spaCy Contributor Agreement (**"SCA"**) is based on the
+[Oracle Contributor Agreement](http://www.oracle.com/technetwork/oca-405177.pdf).
+The SCA applies to any contribution that you make to any product or project
+managed by us (the **"project"**), and sets out the intellectual property rights
+you grant to us in the contributed materials. The term **"us"** shall mean
+[ExplosionAI GmbH](https://explosion.ai/legal). The term
+**"you"** shall mean the person or entity identified below.
+
+If you agree to be bound by these terms, fill in the information requested
+below and include the filled-in version with your first pull request, under the
+folder [`.github/contributors/`](/.github/contributors/). The name of the file
+should be your GitHub username, with the extension `.md`. For example, the user
+example_user would create the file `.github/contributors/example_user.md`.
+
+Read this agreement carefully before signing. These terms and conditions
+constitute a binding legal agreement.
+
+## Contributor Agreement
+
+1. The term "contribution" or "contributed materials" means any source code,
+object code, patch, tool, sample, graphic, specification, manual,
+documentation, or any other material posted or submitted by you to the project.
+
+2. With respect to any worldwide copyrights, or copyright applications and
+registrations, in your contribution:
+
+    * you hereby assign to us joint ownership, and to the extent that such
+    assignment is or becomes invalid, ineffective or unenforceable, you hereby
+    grant to us a perpetual, irrevocable, non-exclusive, worldwide, no-charge,
+    royalty-free, unrestricted license to exercise all rights under those
+    copyrights. This includes, at our option, the right to sublicense these same
+    rights to third parties through multiple levels of sublicensees or other
+    licensing arrangements;
+
+    * you agree that each of us can do all things in relation to your
+    contribution as if each of us were the sole owners, and if one of us makes
+    a derivative work of your contribution, the one who makes the derivative
+    work (or has it made will be the sole owner of that derivative work;
+
+    * you agree that you will not assert any moral rights in your contribution
+    against us, our licensees or transferees;
+
+    * you agree that we may register a copyright in your contribution and
+    exercise all ownership rights associated with it; and
+
+    * you agree that neither of us has any duty to consult with, obtain the
+    consent of, pay or render an accounting to the other for any use or
+    distribution of your contribution.
+
+3. With respect to any patents you own, or that you can license without payment
+to any third party, you hereby grant to us a perpetual, irrevocable,
+non-exclusive, worldwide, no-charge, royalty-free license to:
+
+    * make, have made, use, sell, offer to sell, import, and otherwise transfer
+    your contribution in whole or in part, alone or in combination with or
+    included in any product, work or materials arising out of the project to
+    which your contribution was submitted, and
+
+    * at our option, to sublicense these same rights to third parties through
+    multiple levels of sublicensees or other licensing arrangements.
+
+4. Except as set out above, you keep all right, title, and interest in your
+contribution. The rights that you grant to us under these terms are effective
+on the date you first submitted a contribution to us, even if your submission
+took place before the date you sign these terms.
+
+5. You covenant, represent, warrant and agree that:
+
+    * Each contribution that you submit is and shall be an original work of
+    authorship and you can legally grant the rights set out in this SCA;
+
+    * to the best of your knowledge, each contribution will not violate any
+    third party's copyrights, trademarks, patents, or other intellectual
+    property rights; and
+
+    * each contribution shall be in compliance with U.S. export control laws and
+    other applicable export and import laws. You agree to notify us if you
+    become aware of any circumstance which would make any of the foregoing
+    representations inaccurate in any respect. We may publicly disclose your
+    participation in the project, including the fact that you have signed the SCA.
+
+6. This SCA is governed by the laws of the State of California and applicable
+U.S. Federal law. Any choice of law rules will not apply.
+
+7. Please place an “x” on one of the applicable statement below. Please do NOT
+mark both statements:
+
+    * [x] I am signing on behalf of myself as an individual and no other person
+    or entity, including my employer, has or will have rights with respect to my
+    contributions.
+
+    * [ ] I am signing on behalf of my employer or a legal entity and I have the
+    actual authority to contractually bind that entity.
+
+## Contributor Details
+
+| Field                          | Entry                |
+|------------------------------- | -------------------- |
+| Name                           |      Xiepeng Li      |
+| Company name (if applicable)   |                      |
+| Title or role (if applicable)  |                      |
+| Date                           |      20190810        |
+| GitHub username                |      phiedulxp       |
+| Website (optional)             |                      |

spacy/lang/zh/__init__.py

@@ -6,7 +6,7 @@ from ...language import Language
 from ...tokens import Doc
 from ..tokenizer_exceptions import BASE_EXCEPTIONS
 from .stop_words import STOP_WORDS
-
+from .tag_map import TAG_MAP
 
 class ChineseDefaults(Language.Defaults):
     lex_attr_getters = dict(Language.Defaults.lex_attr_getters)
@@ -14,6 +14,7 @@ class ChineseDefaults(Language.Defaults):
     use_jieba = True
     tokenizer_exceptions = BASE_EXCEPTIONS
     stop_words = STOP_WORDS
+    tag_map = TAG_MAP
     writing_system = {"direction": "ltr", "has_case": False, "has_letters": False}
 
 
@@ -44,4 +45,4 @@ class Chinese(Language):
             return Doc(self.vocab, words=words, spaces=spaces)
 
 
-__all__ = ["Chinese"]
+__all__ = ["Chinese"]

spacy/lang/zh/examples.py

@@ -9,10 +9,12 @@ Example sentences to test spaCy and its language models.
 >>> docs = nlp.pipe(sentences)
 """
 
-
+# from https://zh.wikipedia.org/wiki/汉语
 sentences = [
-    "蘋果公司正考量用一億元買下英國的新創公司",
+    "作为语言而言，为世界使用人数最多的语言，目前世界有五分之一人口做为母语。",
-    "自駕車將保險責任歸屬轉移至製造商",
+    "汉语有多种分支，当中官话最为流行，为中华人民共和国的国家通用语言（又称为普通话）、以及中华民国的国语。",
-    "舊金山考慮禁止送貨機器人在人行道上行駛",
+    "此外，中文还是联合国正式语文，并被上海合作组织等国际组织采用为官方语言。",
-    "倫敦是英國的大城市",
+    "在中国大陆，汉语通称为“汉语”。",
+    "在联合国、台湾、香港及澳门，通称为“中文”。",
+    "在新加坡及马来西亚，通称为“华语”。"
 ]

spacy/lang/zh/lex_attrs.py

@@ -0,0 +1,107 @@
+# coding: utf8
+from __future__ import unicode_literals
+import re
+from ...attrs import LIKE_NUM
+
+_single_num_words = [
+    "〇",
+    "一",
+    "二",
+    "三",
+    "四",
+    "五",
+    "六",
+    "七",
+    "八",
+    "九",
+    "十",
+    "十一",
+    "十二",
+    "十三",
+    "十四",
+    "十五",
+    "十六",
+    "十七",
+    "十八",
+    "十九",
+    "廿",
+    "卅",
+    "卌",
+    "皕",
+    "零",
+    "壹",
+    "贰",
+    "叁",
+    "肆",
+    "伍",
+    "陆",
+    "柒",
+    "捌",
+    "玖",
+    "拾",
+    "拾壹",
+    "拾贰",
+    "拾叁",
+    "拾肆",
+    "拾伍",
+    "拾陆",
+    "拾柒",
+    "拾捌",
+    "拾玖"
+]
+
+_count_num_words = [
+    "一",
+    "二",
+    "三",
+    "四",
+    "五",
+    "六",
+    "七",
+    "八",
+    "九",
+    "壹",
+    "贰",
+    "叁",
+    "肆",
+    "伍",
+    "陆",
+    "柒",
+    "捌",
+    "玖"
+]
+
+_base_num_words = [
+    "十",
+    "百",
+    "千",
+    "万",
+    "亿",
+    "兆",
+    "拾",
+    "佰",
+    "仟"
+]
+
+
+def like_num(text):
+    if text.startswith(("+", "-", "±", "~")):
+        text = text[1:]
+    text = text.replace(",", "").replace(
+        ".", "").replace("，", "").replace("。", "")
+    if text.isdigit():
+        return True
+    if text.count("/") == 1:
+        num, denom = text.split("/")
+        if num.isdigit() and denom.isdigit():
+            return True
+    if text in _single_num_words:
+        return True
+    if re.match('^((' + '|'.join(_count_num_words) + '){1}'
+                + '(' + '|'.join(_base_num_words) + '){1})+'
+                + '(' + '|'.join(_count_num_words) + ')?$', text):
+        return True
+    return False
+
+
+LEX_ATTRS = {LIKE_NUM: like_num}

spacy/lang/zh/tag_map.py

@@ -0,0 +1,47 @@
+# coding: utf8
+from __future__ import unicode_literals
+
+from ...symbols import POS, PUNCT, SYM, ADJ, CONJ, CCONJ, NUM, DET, ADV, ADP, X, VERB
+from ...symbols import NOUN, PROPN, PART, INTJ, SPACE, PRON, AUX
+
+# The Chinese part-of-speech tagger uses the OntoNotes 5 version of the Penn Treebank tag set.
+# We also map the tags to the simpler Google Universal POS tag set.
+
+TAG_MAP = {
+    "AS": {POS: PART},
+    "DEC": {POS: PART},
+    "DEG": {POS: PART},
+    "DER": {POS: PART},
+    "DEV": {POS: PART},
+    "ETC": {POS: PART},
+    "LC": {POS: PART},
+    "MSP": {POS: PART},
+    "SP": {POS: PART},
+    "BA": {POS: X},
+    "FW": {POS: X},
+    "IJ": {POS: INTJ},
+    "LB": {POS: X},
+    "ON": {POS: X},
+    "SB": {POS: X},
+    "X": {POS: X},
+    "URL": {POS: X},
+    "INF": {POS: X},
+    "NN": {POS: NOUN},
+    "NR": {POS: NOUN},
+    "NT": {POS: NOUN},
+    "VA": {POS: VERB},
+    "VC": {POS: VERB},
+    "VE": {POS: VERB},
+    "VV": {POS: VERB},
+    "CD": {POS: NUM},
+    "M": {POS: NUM},
+    "OD": {POS: NUM},
+    "DT": {POS: DET},
+    "CC": {POS: CCONJ},
+    "CS": {POS: CONJ},
+    "AD": {POS: ADV},
+    "JJ": {POS: ADJ},
+    "P": {POS: ADP},
+    "PN": {POS: PRON},
+    "PU": {POS: PUNCT}
+}