Store word-segmented and pos-tagging sentences in different class.

.pylintrc

@@ -7,6 +7,7 @@ disable =
 	missing-docstring,
 	too-many-ancestors,
 	too-many-branches,
+	too-many-instance-attributes,
 
 [FORMAT]
 

README.rst

@@ -81,7 +81,7 @@ Requirements
 * `TreeLib <https://treelib.readthedocs.io>`_ 1.5+
 
 * `CkipClassic <https://ckip-classic.readthedocs.io>`_ 1.0+ [Optional]
-* `CkipTagger <https://pypi.org/project/ckiptagger>`_ 0.1+ [Optional]
+* `CkipTagger <https://pypi.org/project/ckiptagger>`_ 0.1.1+ [Optional]
 
 Usage
 =====

ckipnlp/__init__.py

@@ -6,7 +6,7 @@
 __copyright__ = '2018-2020 CKIP Lab'
 
 __title__ = 'CKIPNLP'
-__version__ = '0.7.2'
+__version__ = '0.8.0dev'
 __description__ = 'CKIP CoreNLP'
 __license__ = 'CC BY-NC-SA 4.0'
 

ckipnlp/container/__init__.py

@@ -11,8 +11,8 @@
 
 from .text import *
 from .seg import *
-from .ws import *
 from .ner import *
 from .parsed import *
 
+from .wspos import *
 from .parsed_tree import *

ckipnlp/container/base.py

@@ -42,8 +42,8 @@ def from_text(cls, data):
     def to_text(self):
         """Transform to plain text.
 
-        Return
-        ------
+        Returns
+        -------
             str
         """
         return NotImplemented
@@ -90,8 +90,8 @@ def from_json(cls, data, **kwargs):
     def to_json(self, **kwargs):
         """Transform to JSON format.
 
-        Return
-        ------
+        Returns
+        -------
             str
         """
         return _json.dumps(self.to_dict(), **kwargs)
@@ -127,8 +127,8 @@ def from_dict(cls, data):
     def to_dict(self):
         """Transform to python built-in containers.
 
-        Return
-        ------
+        Returns
+        -------
             dict
         """
         return self._asdict() # pylint: disable=no-member
@@ -148,8 +148,8 @@ def from_list(cls, data):
     def to_list(self):
         """Transform to python built-in containers.
 
-        Return
-        ------
+        Returns
+        -------
             list
         """
         return list(self)
@@ -177,8 +177,8 @@ def from_text(cls, data):
     def to_text(self):
         """Transform to plain text.
 
-        Return
-        ------
+        Returns
+        -------
             List[str]
         """
         return list(map(self._item_to_text, self))  # pylint: disable=no-member
@@ -199,8 +199,8 @@ def from_dict(cls, data):
     def to_dict(self):
         """Transform to python built-in containers.
 
-        Return
-        ------
+        Returns
+        -------
             List[Container]
         """
         return list(map(self._item_to_dict, self))  # pylint: disable=no-member
@@ -221,8 +221,8 @@ def from_list(cls, data):
     def to_list(self):
         """Transform to python built-in containers.
 
-        Return
-        ------
+        Returns
+        -------
             List[Container]
         """
         return list(map(self._item_to_list, self))  # pylint: disable=no-member

ckipnlp/container/ner.py

@@ -157,7 +157,7 @@ def to_tagger(self):
 
 ################################################################################################################################
 
-class NerSentenceList(_BaseList):
+class NerParagraph(_BaseList):
     """A list of NER sentence.
 
     .. admonition:: Data Structure Examples

ckipnlp/container/parsed.py

@@ -15,7 +15,7 @@
 
 ################################################################################################################################
 
-class ParsedSentenceList(_BaseList0):
+class ParsedParagraph(_BaseList0):
     """A list of parsed sentence.
 
     .. admonition:: Data Structure Examples
@@ -27,8 +27,8 @@ class ParsedSentenceList(_BaseList0):
             .. code-block:: python
 
                 [
-                    '#1:1.[0] S(Head:Nab:中文字|particle:Td:耶)#',                     # Sentence 1
-                    '#2:1.[0] %(particle:I:啊|manner:Dh:哈|manner:Dh:哈|time:Dh:哈)#', # Sentence 2
+                    'S(Head:Nab:中文字|particle:Td:耶)',                     # Sentence 1
+                    '%(particle:I:啊|manner:Dh:哈|manner:Dh:哈|time:Dh:哈)', # Sentence 2
                 ]
     """
 

ckipnlp/container/parsed_tree.py

@@ -351,8 +351,8 @@ def to_text(self, node_id=0):  # pylint: disable=arguments-differ
             node_id : int
                 Output the plain text format for the subtree under **node_id**.
 
-        Return
-        ------
+        Returns
+        --------
             str
         """
         node = self[node_id]
@@ -397,8 +397,8 @@ def to_dict(self, node_id=0):  # pylint: disable=arguments-differ
             node_id : int
                 Output the plain text format for the subtree under **node_id**.
 
-        Return
-        ------
+        Returns
+        -------
             str
         """
         tree_dict = self[node_id].to_dict()

ckipnlp/container/seg.py

@@ -34,6 +34,11 @@ class SegSentence(_BaseSentence0):
             .. code-block:: python
 
                 [ '中文字', '喔', ]
+
+    .. note::
+
+        This class is also used for part-of-speech tagging.
+
     """
 
     item_class = str
@@ -45,7 +50,7 @@ def from_text(cls, data):
     def to_text(self):
         return '\u3000'.join(map(self._item_to_text, self))
 
-class SegSentenceList(_BaseList):
+class SegParagraph(_BaseList):
     """A list of word-segmented sentences.
 
     .. admonition:: Data Structure Examples
@@ -69,6 +74,11 @@ class SegSentenceList(_BaseList):
                     [ '中文字', '喔', ], # Sentence 1
                     [ '啊哈', '哈哈', ], # Sentence 2
                 ]
+
+    .. note::
+
+        This class is also used for part-of-speech tagging.
+
     """
 
     item_class = SegSentence

ckipnlp/container/text.py

@@ -15,7 +15,7 @@
 
 ################################################################################################################################
 
-class TextSentenceList(_BaseList0):
+class TextParagraph(_BaseList0):
     """A list of text sentence.
 
     .. admonition:: Data Structure Examples