chore: prepare v3.1.0

actrie/__init__.py

@@ -1,8 +1,8 @@
 #!/usr/bin/env python
-# coding=utf-8
+# encoding=utf-8
 
 from .matcher import Matcher, Context, PrefixMatcher
 
-__all__ = ['Matcher', 'Context', 'PrefixMatcher']
+__all__ = ["Matcher", "Context", "PrefixMatcher"]
 
-__version__ = '3.0.9'
+__version__ = "3.1.0"

actrie/context.py

@@ -1,4 +1,4 @@
-# coding=utf-8
+# encoding=utf-8
 
 from collections import Iterator
 
@@ -8,7 +8,6 @@
 
 
 class Context(Iterator):
-
     def __init__(self, matcher, content=None, return_byte_pos=False):
         if matcher is None:
             raise MatcherError("Matcher is None")
@@ -32,8 +31,7 @@ def reset(self, content=None, return_byte_pos=None):
             self._content = convert2pass(content)
         if return_byte_pos is not None:
             self._return_byte_pos = return_byte_pos
-        self._uninitialized = not _actrie.ResetContext(
-            self._context, self._content, self._return_byte_pos)
+        self._uninitialized = not _actrie.ResetContext(self._context, self._content, self._return_byte_pos)
         if self._uninitialized:
             raise MatcherError("Reset context failed!")
 
@@ -55,7 +53,6 @@ def next(self):
 
 
 class PrefixContext(Context):
-
     def _next(self):
         if self._uninitialized:
             raise None

actrie/error.py

@@ -1,8 +1,7 @@
-# coding=utf-8
+# encoding=utf-8
 
 
 class MatcherError(Exception):
-
     def __init__(self, value):
         self.value = value
 

actrie/matcher.py

@@ -9,60 +9,71 @@
 
 
 class Matcher:
-
     def __init__(self):
         self._matcher = 0
 
     def __del__(self):
         _actrie.Destruct(self._matcher)
 
-    def load_from_file(self, path, all_as_plain=False, ignore_bad_pattern=False, bad_as_plain=True, deduplicate_extra=True):
+    def load_from_file(
+        self, path, all_as_plain=False, ignore_bad_pattern=False, bad_as_plain=True, deduplicate_extra=True
+    ):
         if self._matcher:
             raise MatcherError("Matcher is already initialized.")
         if not os.path.isfile(path):
             return False
         self._matcher = _actrie.ConstructByFile(
-            convert2pass(path), all_as_plain, ignore_bad_pattern, bad_as_plain, deduplicate_extra)
+            convert2pass(path), all_as_plain, ignore_bad_pattern, bad_as_plain, deduplicate_extra
+        )
         return self._matcher != 0
 
     @classmethod
-    def create_by_file(cls, path, all_as_plain=False, ignore_bad_pattern=False, bad_as_plain=True, deduplicate_extra=True):
+    def create_by_file(
+        cls, path, all_as_plain=False, ignore_bad_pattern=False, bad_as_plain=True, deduplicate_extra=True
+    ):
         matcher = cls()
         if matcher.load_from_file(path, all_as_plain, ignore_bad_pattern, bad_as_plain, deduplicate_extra):
             return matcher
         return None
 
-    def load_from_string(self, keywords, all_as_plain=False, ignore_bad_pattern=False, bad_as_plain=True, deduplicate_extra=True):
+    def load_from_string(
+        self, keywords, all_as_plain=False, ignore_bad_pattern=False, bad_as_plain=True, deduplicate_extra=True
+    ):
         if self._matcher:
             raise MatcherError("Matcher is already initialized.")
         if keywords is None:
             return False
         self._matcher = _actrie.ConstructByString(
-            convert2pass(keywords), all_as_plain, ignore_bad_pattern, bad_as_plain, deduplicate_extra)
+            convert2pass(keywords), all_as_plain, ignore_bad_pattern, bad_as_plain, deduplicate_extra
+        )
         return self._matcher != 0
 
     @classmethod
-    def create_by_string(cls, keywords, all_as_plain=False, ignore_bad_pattern=False, bad_as_plain=True, deduplicate_extra=True):
+    def create_by_string(
+        cls, keywords, all_as_plain=False, ignore_bad_pattern=False, bad_as_plain=True, deduplicate_extra=True
+    ):
         matcher = cls()
         if matcher.load_from_string(keywords, all_as_plain, ignore_bad_pattern, bad_as_plain, deduplicate_extra):
             return matcher
         return None
 
-    def load_from_collection(self, keywords, all_as_plain=False, ignore_bad_pattern=False, bad_as_plain=True, deduplicate_extra=True):
+    def load_from_collection(
+        self, keywords, all_as_plain=False, ignore_bad_pattern=False, bad_as_plain=True, deduplicate_extra=True
+    ):
         if self._matcher:
             raise MatcherError("Matcher is already initialized.")
         if isinstance(keywords, list) or isinstance(keywords, set):
             # for utf-8 '\n' is 0x0a, in other words, utf-8 is ascii compatible.
             # but in python3, str.join is only accept str as argument
-            keywords = "\n".join(
-                [convert2pass(keyword) for keyword in keywords
-                 if convert2pass(keyword)])
+            keywords = "\n".join([convert2pass(keyword) for keyword in keywords if convert2pass(keyword)])
         else:
             raise MatcherError("Keywords should be list or set.")
         return self.load_from_string(keywords, all_as_plain, ignore_bad_pattern, bad_as_plain, deduplicate_extra)
 
     @classmethod
-    def create_by_collection(cls, keywords, all_as_plain=False, ignore_bad_pattern=False, bad_as_plain=True, deduplicate_extra=True):
+    def create_by_collection(
+        cls, keywords, all_as_plain=False, ignore_bad_pattern=False, bad_as_plain=True, deduplicate_extra=True
+    ):
         matcher = cls()
         if matcher.load_from_collection(keywords, all_as_plain, ignore_bad_pattern, bad_as_plain, deduplicate_extra):
             return matcher
@@ -99,7 +110,6 @@ def search(self, content, return_byte_pos=False):
 
 
 class PrefixMatcher(Matcher):
-
     def match(self, content, return_byte_pos=False):
         if not self._matcher:
             raise MatcherError("Matcher is not initialized.")

actrie/pattern.py

@@ -4,10 +4,12 @@
 
 try:
     from enum import Enum
-except:
+except Exception:
+
     class Enum(object):
         pass
 
+
 from .tokenizer import Tokenizer
 from .util import convert2unicode, is_py3k
 
@@ -149,7 +151,7 @@ def _parse_all(tokenizer, stop=None):
 
     @abstractmethod
     def ustr(self):
-        return u''
+        return u""
 
 
 class PurePattern(Pattern):
@@ -165,7 +167,7 @@ def ustr(self):
         return self.text
 
     def __str__(self):
-        return self.ustr() if is_py3k else self.ustr().encode('utf-8')
+        return self.ustr() if is_py3k else self.ustr().encode("utf-8")
 
 
 class AlternationPattern(Pattern):
@@ -181,7 +183,7 @@ def ustr(self):
             return u"(" + u"|".join([p.ustr() for p in self.alters]) + u")"
 
     def __str__(self):
-        return self.ustr() if is_py3k else self.ustr().encode('utf-8')
+        return self.ustr() if is_py3k else self.ustr().encode("utf-8")
 
 
 class AntiAmbiguousPattern(Pattern):
@@ -195,7 +197,7 @@ def ustr(self):
         return self.origin.ustr() + u"(?&!" + u"|".join([p.ustr() for p in self.ambis]) + u")"
 
     def __str__(self):
-        return self.ustr() if is_py3k else self.ustr().encode('utf-8')
+        return self.ustr() if is_py3k else self.ustr().encode("utf-8")
 
 
 class DistancePattern(Pattern):
@@ -210,4 +212,5 @@ def ustr(self):
         return self.head.ustr() + u".{0," + convert2unicode(str(self.dist)) + u"}" + self.tail.ustr()
 
     def __str__(self):
-        return self.ustr() if is_py3k else self.ustr().encode('utf-8')
+        return self.ustr() if is_py3k else self.ustr().encode("utf-8")
+

actrie/tokenizer.py

@@ -15,7 +15,6 @@ def __str__(self):
 
 
 class Tokenizer:
-
     def __init__(self, text):
         self.text = text
         self.cur = 0
@@ -73,7 +72,7 @@ def consume_integer(self):
 
     def expect(self, s, move=True):
         wlen = len(s)
-        if len(self.text) - self.cur >= wlen and self.text[self.cur:(self.cur + wlen)] == s:
+        if len(self.text) - self.cur >= wlen and self.text[self.cur : (self.cur + wlen)] == s:
             if move:
                 self.cur += wlen
             return True

actrie/util.py

@@ -2,34 +2,66 @@
 
 import sys
 
-is_py3k = bool(sys.version_info[0] == 3)
+try:
+    from typing import AnyStr
+except Exception:
+    pass
 
+is_py2k = bool(sys.version_info[0] == 2)
 
-def convert2pass(obj):
-    if is_py3k:
-        if isinstance(obj, bytes):
-            return obj.decode("utf-8")
-    else:
-        if isinstance(obj, unicode):
-            return obj.encode("utf-8")
-    return obj
+if not is_py2k:
 
+    def convert2pass(string):
+        # type: (AnyStr) -> str
+        if isinstance(string, bytes):
+            return string.decode("utf-8")
+        return string
 
-def convert2unicode(obj):
-    if is_py3k:
-        if isinstance(obj, bytes):
-            return obj.decode("utf-8")
-    else:
-        if isinstance(obj, str):
-            return obj.decode("utf-8")
-    return obj
+    def convert2unicode(string):
+        # type: (AnyStr) -> str
+        if isinstance(string, bytes):
+            return string.decode("utf-8")
+        return string
 
-
-def replace_escap(word):
-    if is_py3k or isinstance(str, unicode):
-        for old, new in ((u"\\", u"\\\\"), (u"(", u"\\("), (u")", u"\\)"), (u"{", u"\\{"), (u".", u"\\."), (u"|", u"\\|")):
-            word = word.replace(old, new)
-    else:
-        for old, new in (("\\", "\\\\"), ("(", "\\("), (")", "\\)"), ("{", "\\{"), (".", "\\."), ("|", "\\|")):
+    def replace_escap(word):
+        for old, new in (
+            (u"\\", u"\\\\"),
+            (u"(", u"\\("),
+            (u")", u"\\)"),
+            (u"{", u"\\{"),
+            (u".", u"\\."),
+            (u"|", u"\\|"),
+        ):
             word = word.replace(old, new)
-    return word
+        return word
+
+
+else:
+
+    def convert2pass(string):
+        # type: (AnyStr) -> str
+        if isinstance(string, unicode):
+            return string.encode("utf-8")
+        return string
+
+    def convert2unicode(string):
+        # type: (AnyStr) -> unicode
+        if isinstance(string, str):
+            return string.decode("utf-8")
+        return string
+
+    def replace_escap(word):
+        if isinstance(word, unicode):
+            for old, new in (
+                (u"\\", u"\\\\"),
+                (u"(", u"\\("),
+                (u")", u"\\)"),
+                (u"{", u"\\{"),
+                (u".", u"\\."),
+                (u"|", u"\\|"),
+            ):
+                word = word.replace(old, new)
+        else:
+            for old, new in (("\\", "\\\\"), ("(", "\\("), (")", "\\)"), ("{", "\\{"), (".", "\\."), ("|", "\\|")):
+                word = word.replace(old, new)
+        return word

jni/pom.xml

@@ -4,7 +4,7 @@
 
     <groupId>psn.ifplusor</groupId>
     <artifactId>actrie</artifactId>
-    <version>3.0.9</version>
+    <version>3.1.0</version>
     <packaging>nar</packaging>
 
     <name>actrie</name>