From ee061282224fcbb9a0bd486fbc6ddff53ffbb421 Mon Sep 17 00:00:00 2001
From: Patrick Watrin <pat@lucy.local>
Date: Thu, 25 Feb 2016 12:56:41 +0100
Subject: [PATCH] PEP 0008 cosmetics
---
unitex/__init__.py | 16 ++++++-----
unitex/io.py | 47 ++++++++++++++++++--------------
unitex/resources.py | 60 +++++++++++++++++++++++------------------
unitex/tools.py | 65 +++++++++++++++++++++++++++------------------
4 files changed, 110 insertions(+), 78 deletions(-)
diff --git a/unitex/__init__.py b/unitex/__init__.py
index 771fd87..ed95843 100644
--- a/unitex/__init__.py
+++ b/unitex/__init__.py
@@ -111,11 +111,12 @@ _LOGGER = logging.getLogger(__name__)
def enable_stdout():
"""
- This function enables Unitex standard output. This is the default but
- should be used for debug purposes only.
+ This function enables Unitex standard output. This is the default
+ but should be used for debug purposes only.
Return [bool]:
- The function returns 'True' if it succeeds and 'False' otherwise.
+ The function returns 'True' if it succeeds and 'False'
+ otherwise.
"""
_LOGGER.info("Enabling standard output...")
ret = unitex_enable_stdout()
@@ -131,7 +132,8 @@ def disable_stdout():
improve performances.
Return [bool]:
- The function returns 'True' if it succeeds and 'False' otherwise.
+ The function returns 'True' if it succeeds and 'False'
+ otherwise.
"""
_LOGGER.info("Disabling standard output...")
ret = unitex_disable_stdout()
@@ -146,7 +148,8 @@ def enable_stderr():
should be used for debug purposes only.
Return [bool]:
- The function returns 'True' if it succeeds and 'False' otherwise.
+ The function returns 'True' if it succeeds and 'False'
+ otherwise.
"""
_LOGGER.info("Enabling error output...")
ret = unitex_enable_stderr()
@@ -162,7 +165,8 @@ def disable_stderr():
improve performances.
Return [bool]:
- The function returns 'True' if it succeeds and 'False' otherwise.
+ The function returns 'True' if it succeeds and 'False'
+ otherwise.
"""
_LOGGER.info("Disabling error output...")
ret = unitex_disable_stderr()
diff --git a/unitex/io.py b/unitex/io.py
index f633974..0244d50 100644
--- a/unitex/io.py
+++ b/unitex/io.py
@@ -22,16 +22,17 @@ _LOGGER = logging.getLogger(__name__)
def cp(source_path, target_path):
"""
- This function copies a file. Both pathes can be on the virtual filesystem
- or the disk filesystem. Therefor, this function can be used to virtualize a
- file or to dump a virtual file.
+ This function copies a file. Both pathes can be on the virtual
+ filesystem or the disk filesystem. Therefor, this function can be
+ used to virtualize a file or to dump a virtual file.
Arguments:
source_path [str] -- source file path
target_path [str] -- target file path
Return [bool]:
- The function returns 'True' if it succeeds and 'False' otherwise.
+ The function returns 'True' if it succeeds and 'False'
+ otherwise.
"""
_LOGGER.info("Copying file '%s' to '%s'..." % (source_path, target_path))
ret = unitex_cp(source_path, target_path)
@@ -42,14 +43,15 @@ def cp(source_path, target_path):
def rm(path):
"""
- This function removes a file. The path can be on the virtual filesystem
- or the disk filesystem.
+ This function removes a file. The path can be on the virtual
+ filesystem or the disk filesystem.
Argument:
path [str] -- file path
Return [bool]:
- The function returns 'True' if it succeeds and 'False' otherwise.
+ The function returns 'True' if it succeeds and 'False'
+ otherwise.
"""
_LOGGER.info("Removing file '%s'..." % path)
ret = unitex_rm(path)
@@ -60,15 +62,16 @@ def rm(path):
def mv(old_path, new_path):
"""
- This function moves/renames a file. Both pathes can be on the virtual
- filesystem or the disk filesystem.
+ This function moves/renames a file. Both pathes can be on the
+ virtual filesystem or the disk filesystem.
Arguments:
old_path [str] -- old file path
new_path [str] -- new file path
Return [bool]:
- The function returns 'True' if it succeeds and 'False' otherwise.
+ The function returns 'True' if it succeeds and 'False'
+ otherwise.
"""
_LOGGER.info("Moving file '%s' to '%s'..." % (old_path, new_path))
ret = unitex_mv(old_path, new_path)
@@ -85,7 +88,8 @@ def mkdir(path):
path [str] -- directory path
Return [bool]:
- The function returns 'True' if it succeeds and 'False' otherwise.
+ The function returns 'True' if it succeeds and 'False'
+ otherwise.
"""
_LOGGER.info("Creating directory '%s'..." % path)
ret = unitex_mkdir(path)
@@ -102,7 +106,8 @@ def rmdir(path):
path [str] -- directory path
Return [bool]:
- The function returns 'True' if it succeeds and 'False' otherwise.
+ The function returns 'True' if it succeeds and 'False'
+ otherwise.
"""
_LOGGER.info("Removing directory '%s'..." % path)
ret = unitex_rmdir(path)
@@ -119,21 +124,23 @@ def ls(path):
path [str] -- directory path
Return [list(str)]:
- The function returns a list of files (not directories) if the directory
- is not empty and an empty list otherwise.
+ The function returns a list of files (not directories) if the
+ directory is not empty and an empty list otherwise.
"""
_LOGGER.info("Listing directory '%s'..." % path)
return unitex_ls(path)
def exists(path):
"""
- This function verify if a file exists (on disk or virtual filesystem).
+ This function verify if a file exists (on disk or virtual
+ filesystem).
Argument:
path [str] -- directory path
Return [bool]:
- The function returns 'True' if it succeeds and 'False' otherwise.
+ The function returns 'True' if it succeeds and 'False'
+ otherwise.
"""
if path.startswith(UnitexConstants.VFS_PREFIX) is False:
return os.path.exists(path)
@@ -144,11 +151,11 @@ def exists(path):
class UnitexFile(object):
"""
The UnitexFile class provides the minimum functionality necessary to
- manipulate files on the disk and the virtual filesystems. It's mainly
- useful to read files from virtual filesystem whithout having to copy them
- to the disk.
+ manipulate files on the disk and the virtual filesystems. It's
+ mainly useful to read files from virtual filesystem whithout having
+ to copy them to the disk.
- **WARNING: the encoding must be UTF-8 and the data Unicode strings.**
+ *WARNING: the encoding must be UTF-8 and the data Unicode strings.*
"""
def __init__(self):
diff --git a/unitex/resources.py b/unitex/resources.py
index b57be97..5301d69 100644
--- a/unitex/resources.py
+++ b/unitex/resources.py
@@ -24,25 +24,28 @@ def load_persistent_dictionary(path):
This function loads a dictionary in persistent space.
Argument:
- path [str] -- the exisent file path in filespace (hard disk or virtual file system)
+ path [str] -- the exisent file path in filespace (hard disk or
+ virtual file system).
Return [str]:
- The persistent file path [str] (derived from filename but not strictly identical,
- depending of implementation). This path must be used by the unitex tools and the
- 'free_persistent_dictionary' function.
+ The persistent file path [str] (derived from filename but not
+ strictly identical, depending of implementation). This path must
+ be used by the unitex tools and the 'free_persistent_dictionary'
+ function.
"""
_LOGGER.info("Load persistent dictionary '%s'..." % path)
return unitex_load_persistent_dictionary(path)
def is_persistent_dictionary(path):
"""
- This function checks if a dictionary path points to the persistent space.
+ This function checks if a dictionary path points to the persistent
+ space.
Argument:
- path [str] -- the file path to check
+ path [str] -- the file path to check.
Return [bool]:
- True if the dictionary is persitent otherwise False
+ True if the dictionary is persitent otherwise False.
"""
return unitex_is_persistent_dictionary(path)
@@ -51,8 +54,8 @@ def free_persistent_dictionary(path):
This function unloads a dictionary from persistent space.
Argument:
- path [str] -- the persistent file path returned by the 'load_persistent_dictionary'
- function
+ path [str] -- the persistent file path returned by the
+ 'load_persistent_dictionary' function.
"""
_LOGGER.info("Free persistent dictionary '%s'..." % path)
unitex_free_persistent_dictionary(path)
@@ -64,12 +67,14 @@ def load_persistent_fst2(path):
This function loads a fst2 in persistent space.
Argument:
- path [str] -- the exisent file path in filespace (hard disk or virtual file system)
+ path [str] -- the exisent file path in filespace (hard disk or
+ virtual file system).
Return [str]:
- The persistent file path [str] (derived from filename but not strictly identical,
- depending of implementation). This path must be used by the unitex tools and the
- 'free_persistent_fst2' function.
+ The persistent file path [str] (derived from filename but not
+ strictly identical, depending of implementation). This path must
+ be used by the unitex tools and the 'free_persistent_fst2'
+ function.
"""
_LOGGER.info("Load persistent fst2 '%s'..." % path)
return unitex_load_persistent_fst2(path)
@@ -79,10 +84,10 @@ def is_persistent_fst2(path):
This function checks if a fst2 path points to the persistent space.
Argument:
- path [str] -- the file path to check
+ path [str] -- the file path to check.
Return [bool]:
- True if the fst2 is persitent otherwise False
+ True if the fst2 is persitent otherwise False.
"""
return unitex_is_persistent_fst2(path)
@@ -91,8 +96,8 @@ def free_persistent_fst2(path):
This function unloads a fst2 from persistent space.
Argument:
- path [str] -- the persistent file path returned by the 'load_persistent_fst2'
- function
+ path [str] -- the persistent file path returned by the
+ 'load_persistent_fst2' function.
"""
_LOGGER.info("Free persistent fst2 '%s'..." % path)
unitex_free_persistent_fst2(path)
@@ -104,25 +109,28 @@ def load_persistent_alphabet(path):
This function loads a alphabet in persistent space.
Argument:
- path [str] -- the exisent file path in filespace (hard disk or virtual file system)
+ path [str] -- the exisent file path in filespace (hard disk or
+ virtual file system).
Return [str]:
- The persistent file path [str] (derived from filename but not strictly identical,
- depending of implementation). This path must be used by the unitex tools and the
- 'free_persistent_alphabet' function.
+ The persistent file path [str] (derived from filename but not
+ strictly identical, depending of implementation). This path must
+ be used by the unitex tools and the 'free_persistent_alphabet'
+ function.
"""
_LOGGER.info("Load persistent alphabet '%s'..." % path)
return unitex_load_persistent_alphabet(path)
def is_persistent_alphabet(path):
"""
- This function checks if a alphabet path points to the persistent space.
+ This function checks if a alphabet path points to the persistent
+ space.
Argument:
- path [str] -- the file path to check
+ path [str] -- the file path to check.
Return [bool]:
- True if the alphabet is persitent otherwise False
+ True if the alphabet is persitent otherwise False.
"""
return unitex_is_persistent_alphabet(path)
@@ -131,8 +139,8 @@ def free_persistent_alphabet(path):
This function unloads a alphabet from persistent space.
Argument:
- path [str] -- the persistent file path returned by the 'load_persistent_alphabet'
- function
+ path [str] -- the persistent file path returned by the
+ 'load_persistent_alphabet' function.
"""
_LOGGER.info("Free persistent alphabet '%s'..." % path)
unitex_free_persistent_alphabet(path)
diff --git a/unitex/tools.py b/unitex/tools.py
index 74cbedd..82c5df7 100644
--- a/unitex/tools.py
+++ b/unitex/tools.py
@@ -31,17 +31,23 @@ def check_dic(dictionary, dtype, alphabet, **kwargs):
stored in the <dela> directory.
Arguments:
- dictionary [str] -- the dictionary file path
- dtype [str] -- the dictionary type: UnitexConstants.DELAF (inflected)
- UnitexConstants.DELAS (non inflected)
- alphabet [str] -- the alphabet file path
+ dictionary [str] -- the dictionary file path.
+
+ dtype [str] -- the dictionary type:
+ - UnitexConstants.DELAF (inflected);
+ - UnitexConstants.DELAS (non inflected).
+
+ alphabet [str] -- the alphabet file path.
Keyword arguments:
- strict [bool] -- strict syntax checking against unprotected dot and comma (default: False)
- no_space_warning [bool] -- tolerates spaces in grammatical/semantic/inflectional codes (default: True)
+ strict [bool] -- strict syntax checking against unprotected dot
+ and comma (default: False).
+
+ no_space_warning [bool] -- tolerates spaces in grammatical,
+ semantic and inflectional codes (default: True).
Return [bool]:
- The function returns 'True' if it succeeds and 'False' otherwise.
+ True if it succeeds and False otherwise.
"""
options = CheckDicOptions()
options.load(kwargs)
@@ -78,30 +84,37 @@ def check_dic(dictionary, dtype, alphabet, **kwargs):
def compress(dictionary, **kwargs):
"""
- This function takes a DELAF dictionary as a parameter and compresses it. The
- compression of a dictionary dico.dic produces two files:
+ This function takes a DELAF dictionary as a parameter and compresses
+ it. The compression of a dictionary dico.dic produces two files:
+
+ - dico.bin: a binary file containing the minimum automaton of
+ the inflected forms of the dictionary;
- - dico.bin: a binary file containing the minimum automaton of the inflected
- forms of the dictionary;
- - dico.inf: a text file containing the compressed forms required for the reconstruction
- of the dictionary lines from the inflected forms contained in the
- automaton.
+ - dico.inf: a text file containing the compressed forms required
+ for the reconstruction of the dictionary lines from the
+ inflected forms contained in the automaton.
Arguments:
- dictionary [str] -- the dictionary file path
+ dictionary [str] -- the dictionary file path.
Keyword arguments:
- output [str] -- sets the output file. By default, a file xxx.dic will
- produce a file xxx.bin
- flip [bool] -- indicates that the inflected and canonical forms should be swapped in the
- compressed dictionary. This option is used to construct an inverse dictionary
- which is necessary for the program 'Reconstrucao' (default: False)
- semitic [bool] -- indicates that the semitic compression algorithm should be used. Setting this
- option with semitic languages like Arabic significantly reduces the size of
- the output dictionary (default: False)
- version [str] -- 'v1': produces an old style .bin file
- 'v2': produces a new style .bin file, with no file size limitation to 16 Mb
- and a smaller size (default)
+ output [str] -- sets the output file. By default, a file xxx.dic
+ will produce a file xxx.bin.
+
+ flip [bool] -- indicates that the inflected and canonical forms
+ should be swapped in the compressed dictionary. This option
+ is used to construct an inverse dictionary which is
+ necessary for the program 'Reconstrucao' (default: False).
+
+ semitic [bool] -- indicates that the semitic compression
+ algorithm should be used. Setting this option with semitic
+ languages like Arabic significantly reduces the size of the
+ output dictionary (default: False).
+
+ version [str] -- 'v1': produces an old style .bin file;
+ 'v2': produces a new style .bin file, with no
+ file size limitation to 16 Mb and a
+ smaller size (default).
Return [bool]:
The function return 'True' if it succeeds and 'False' otherwise.
--
GitLab