Moving userNameToFileName to its own file, adding unit test

This commit is contained in:
Bill Amidei 2017-12-22 10:46:03 -08:00 committed by Cosimo Lupo
parent abed27fd8c
commit ccae4687cc
No known key found for this signature in database
GPG Key ID: 59D54DB0C9976482
2 changed files with 264 additions and 0 deletions

View File

@ -0,0 +1,207 @@
"""
User name to file name conversion.
This was taken form the UFO 3 spec.
"""
from __future__ import unicode_literals
from fontTools.misc.py23 import basestring, unicode
illegalCharacters = "\" * + / : < > ? [ \ ] | \0".split(" ")
illegalCharacters += [chr(i) for i in range(1, 32)]
illegalCharacters += [chr(0x7F)]
reservedFileNames = "CON PRN AUX CLOCK$ NUL A:-Z: COM1".lower().split(" ")
reservedFileNames += "LPT1 LPT2 LPT3 COM2 COM3 COM4".lower().split(" ")
maxFileNameLength = 255
class NameTranslationError(Exception):
pass
# ----------------------
# User Name to File Name
# ----------------------
# This code was taken directly from the ufoNormalizer script in the unified-font-object repositry
# (https://github.com/unified-font-object/)
# ...which algorithm was taken directly from the UFO 3 specification
def userNameToFileName(userName, existing=[], prefix="", suffix=""):
"""
existing should be a case-insensitive list
of all existing file names.
>>> userNameToFileName("a") == "a"
True
>>> userNameToFileName("A") == "A_"
True
>>> userNameToFileName("AE") == "A_E_"
True
>>> userNameToFileName("Ae") == "A_e"
True
>>> userNameToFileName("ae") == "ae"
True
>>> userNameToFileName("aE") == "aE_"
True
>>> userNameToFileName("a.alt") == "a.alt"
True
>>> userNameToFileName("A.alt") == "A_.alt"
True
>>> userNameToFileName("A.Alt") == "A_.A_lt"
True
>>> userNameToFileName("A.aLt") == "A_.aL_t"
True
>>> userNameToFileName(u"A.alT") == "A_.alT_"
True
>>> userNameToFileName("T_H") == "T__H_"
True
>>> userNameToFileName("T_h") == "T__h"
True
>>> userNameToFileName("t_h") == "t_h"
True
>>> userNameToFileName("F_F_I") == "F__F__I_"
True
>>> userNameToFileName("f_f_i") == "f_f_i"
True
>>> userNameToFileName("Aacute_V.swash") == "A_acute_V_.swash"
True
>>> userNameToFileName(".notdef") == "_notdef"
True
>>> userNameToFileName("con") == "_con"
True
>>> userNameToFileName("CON") == "C_O_N_"
True
>>> userNameToFileName("con.alt") == "_con.alt"
True
>>> userNameToFileName("alt.con") == "alt._con"
True
"""
# the incoming name must be a unicode string
if not isinstance(userName, unicode):
raise ValueError("The value for userName must be a unicode string.")
# establish the prefix and suffix lengths
prefixLength = len(prefix)
suffixLength = len(suffix)
# replace an initial period with an _
# if no prefix is to be added
if not prefix and userName[0] == ".":
userName = "_" + userName[1:]
# filter the user name
filteredUserName = []
for character in userName:
# replace illegal characters with _
if character in illegalCharacters:
character = "_"
# add _ to all non-lower characters
elif character != character.lower():
character += "_"
filteredUserName.append(character)
userName = "".join(filteredUserName)
# clip to 255
sliceLength = maxFileNameLength - prefixLength - suffixLength
userName = userName[:sliceLength]
# test for illegal files names
parts = []
for part in userName.split("."):
if part.lower() in reservedFileNames:
part = "_" + part
parts.append(part)
userName = ".".join(parts)
# test for clash
fullName = prefix + userName + suffix
if fullName.lower() in existing:
fullName = handleClash1(userName, existing, prefix, suffix)
# finished
return fullName
def handleClash1(userName, existing=[], prefix="", suffix=""):
"""
existing should be a case-insensitive list
of all existing file names.
>>> prefix = ("0" * 5) + "."
>>> suffix = "." + ("0" * 10)
>>> existing = ["a" * 5]
>>> e = list(existing)
>>> handleClash1(userName="A" * 5, existing=e,
... prefix=prefix, suffix=suffix) == (
... '00000.AAAAA000000000000001.0000000000')
True
>>> e = list(existing)
>>> e.append(prefix + "aaaaa" + "1".zfill(15) + suffix)
>>> handleClash1(userName="A" * 5, existing=e,
... prefix=prefix, suffix=suffix) == (
... '00000.AAAAA000000000000002.0000000000')
True
>>> e = list(existing)
>>> e.append(prefix + "AAAAA" + "2".zfill(15) + suffix)
>>> handleClash1(userName="A" * 5, existing=e,
... prefix=prefix, suffix=suffix) == (
... '00000.AAAAA000000000000001.0000000000')
True
"""
# if the prefix length + user name length + suffix length + 15 is at
# or past the maximum length, silce 15 characters off of the user name
prefixLength = len(prefix)
suffixLength = len(suffix)
if prefixLength + len(userName) + suffixLength + 15 > maxFileNameLength:
l = (prefixLength + len(userName) + suffixLength + 15)
sliceLength = maxFileNameLength - l
userName = userName[:sliceLength]
finalName = None
# try to add numbers to create a unique name
counter = 1
while finalName is None:
name = userName + str(counter).zfill(15)
fullName = prefix + name + suffix
if fullName.lower() not in existing:
finalName = fullName
break
else:
counter += 1
if counter >= 999999999999999:
break
# if there is a clash, go to the next fallback
if finalName is None:
finalName = handleClash2(existing, prefix, suffix)
# finished
return finalName
def handleClash2(existing=[], prefix="", suffix=""):
"""
existing should be a case-insensitive list
of all existing file names.
>>> prefix = ("0" * 5) + "."
>>> suffix = "." + ("0" * 10)
>>> existing = [prefix + str(i) + suffix for i in range(100)]
>>> e = list(existing)
>>> handleClash2(existing=e, prefix=prefix, suffix=suffix) == (
... '00000.100.0000000000')
True
>>> e = list(existing)
>>> e.remove(prefix + "1" + suffix)
>>> handleClash2(existing=e, prefix=prefix, suffix=suffix) == (
... '00000.1.0000000000')
True
>>> e = list(existing)
>>> e.remove(prefix + "2" + suffix)
>>> handleClash2(existing=e, prefix=prefix, suffix=suffix) == (
... '00000.2.0000000000')
True
"""
# calculate the longest possible string
maxLength = maxFileNameLength - len(prefix) - len(suffix)
maxValue = int("9" * maxLength)
# try to find a number
finalName = None
counter = 1
while finalName is None:
fullName = prefix + str(counter) + suffix
if fullName.lower() not in existing:
finalName = fullName
break
else:
counter += 1
if counter >= maxValue:
break
# raise an error if nothing has been found
if finalName is None:
raise NameTranslationError("No unique name could be found.")
# finished
return finalName

View File

@ -0,0 +1,57 @@
from __future__ import unicode_literals
import unittest
from fontTools.misc.filenames import userNameToFileName
class FilenamesTest(unittest.TestCase):
def test_names(self):
self.assertEqual(userNameToFileName("a"),"a")
self.assertEqual(userNameToFileName("A"), "A_")
self.assertEqual(userNameToFileName("AE"), "A_E_")
self.assertEqual(userNameToFileName("Ae"), "A_e")
self.assertEqual(userNameToFileName("ae"), "ae")
self.assertEqual(userNameToFileName("aE"), "aE_")
self.assertEqual(userNameToFileName("a.alt"), "a.alt")
self.assertEqual(userNameToFileName("A.alt"), "A_.alt")
self.assertEqual(userNameToFileName("A.Alt"), "A_.A_lt")
self.assertEqual(userNameToFileName("A.aLt"), "A_.aL_t")
self.assertEqual(userNameToFileName(u"A.alT"), "A_.alT_")
self.assertEqual(userNameToFileName("T_H"), "T__H_")
self.assertEqual(userNameToFileName("T_h"), "T__h")
self.assertEqual(userNameToFileName("t_h"), "t_h")
self.assertEqual(userNameToFileName("F_F_I"), "F__F__I_")
self.assertEqual(userNameToFileName("f_f_i"), "f_f_i")
self.assertEqual(userNameToFileName("Aacute_V.swash"), "A_acute_V_.swash")
self.assertEqual(userNameToFileName(".notdef"), "_notdef")
self.assertEqual(userNameToFileName("con"), "_con")
self.assertEqual(userNameToFileName("CON"), "C_O_N_")
self.assertEqual(userNameToFileName("con.alt"), "_con.alt")
self.assertEqual(userNameToFileName("alt.con"), "alt._con")
def test_prefix_suffix(self):
PREFIX="TEST_PREFIX"
SUFFIX="TEST_SUFFIX"
NAME="NAME"
NAME_FILE="N_A_M_E_"
self.assertEqual(userNameToFileName(NAME, prefix=PREFIX, suffix=SUFFIX), PREFIX + NAME_FILE + SUFFIX)
def test_collide(self):
PREFIX="TEST_PREFIX"
SUFFIX="TEST_SUFFIX"
NAME="NAME"
NAME_FILE="N_A_M_E_"
COLLISION_AVOIDANCE1="000000000000001"
COLLISION_AVOIDANCE2="000000000000002"
exist = set()
generated = userNameToFileName(NAME, exist, prefix=PREFIX, suffix=SUFFIX)
exist.add(generated.lower())
self.assertEqual(generated, PREFIX + NAME_FILE + SUFFIX)
generated = userNameToFileName(NAME, exist, prefix=PREFIX, suffix=SUFFIX)
exist.add(generated.lower())
self.assertEqual(generated, PREFIX + NAME_FILE + COLLISION_AVOIDANCE1 + SUFFIX)
generated = userNameToFileName(NAME, exist, prefix=PREFIX, suffix=SUFFIX)
self.assertEqual(generated, PREFIX + NAME_FILE + COLLISION_AVOIDANCE2+ SUFFIX)
if __name__ == "__main__":
import sys
sys.exit(unittest.main())