def generateFlat(path,
onlySupported=True,
scriptSeparator=None,
scriptAsPrefix=None,
status=0,
includeUnicodeCategory=False):
data = [
"# Glyph Name Formatted Unicode List - GNFUL",
"# GlyphNameFormatter version %s" % _versionNumber,
"# Unicode version: %s" % unicodeVersion,
"# Source code: %s" % _githubLink,
"# Generated on %s" % time.strftime("%Y %m %d %H:%M:%S"),
]
if includeUnicodeCategory:
data.append("# <glyphName> <hex unicode> <unicodeCategory>")
else:
data.append("# <glyphName> <hex unicode>")
if scriptSeparator is not None:
data.append("# Separator \"%s\"" % scriptSeparator)
if scriptAsPrefix is not None:
data.append("# Prefixed \"%s\"" % scriptAsPrefix)
data.append("#")
for rangeName in getAllRangeNames():
if onlySupported:
moduleName = rangeNameToModuleName(rangeName)
try:
module = importlib.import_module(
'glyphNameFormatter.rangeProcessors.%s' % moduleName)
except:
continue
data.append("# %s" % rangeName)
start, end = getRangeByName(rangeName)
for u in range(start, end + 1):
g = GlyphName(uniNumber=u,
scriptSeparator=scriptSeparator,
scriptAsPrefix=scriptAsPrefix)
g.compress() # should auto compress
if status is not None:
if g.status < status:
# if the glyph has a status that is less than what we're looking for
# then do not include it in the list.
continue
name = g.getName(extension=True)
if name is None:
continue
if includeUnicodeCategory:
data.append("%s %04X %s" %
(name, u, unicodeCategories.get(u, "-")))
else:
data.append("%s %04X" % (name, u))
f = open(path, "w")
f.write("\n".join(data))
f.close()
def testAllPrefixes():
# let's not just assume all prefixes that end up the same
# will also be able to disambiguate names.
from glyphNameFormatter.unicodeRangeNames import getAllRangeNames
prefixes = {}
for n in getAllRangeNames():
pf = scriptPrefixes[n]
if pf not in prefixes:
prefixes[pf] = []
prefixes[pf].append(n)
from pprint import pprint
pprint(prefixes)
def testAllPrefixes():
# let's not just assume all prefixes that end up the same
# will also be able to disambiguate names.
from glyphNameFormatter.unicodeRangeNames import getAllRangeNames
prefixes = {}
for n in getAllRangeNames():
pf = scriptPrefixes[n]
if pf not in prefixes:
prefixes[pf] = []
prefixes[pf].append(n)
from pprint import pprint
pprint(prefixes)
def testAGDCoverage():
wantRanges = []
glyphCount = {}
for name in name2unicode_AGD:
uniNumber = name2unicode_AGD[name]
thisRange = getRangeName(uniNumber)
if thisRange == "Private Use Area":
continue
if thisRange not in glyphCount:
glyphCount[thisRange] = 0
glyphCount[thisRange] += 1
if thisRange is None:
continue
if thisRange not in wantRanges:
wantRanges.append(thisRange)
supported = []
notSupported = []
notNeeded = []
for name in wantRanges:
if name == "Private Use Area":
continue
moduleName = rangeNameToModuleName(name)
try:
module = importlib.import_module('glyphNameFormatter.rangeProcessors.%s' % moduleName)
supported.append(name)
except ImportError:
notSupported.append(name)
for name in getAllRangeNames():
if name not in supported and name not in notSupported:
notNeeded.append(name)
supported.sort()
notSupported.sort()
notNeeded.sort()
supportedTotal = 0
notSupportedTotal = 0
print("Available range processors for AGD:")
for n in supported:
print("\t%8d\t%s" % (glyphCount[n], n))
supportedTotal += glyphCount[n]
print("\nMissing range processors for AGD:")
for n in notSupported:
print("\t%8d\t%s" % (glyphCount[n], n))
notSupportedTotal += glyphCount[n]
print("Supported total", supportedTotal+notSupportedTotal)
print("AGD supported total", supportedTotal)
print("AGD total", len(name2unicode_AGD))
print("Coverage complete: %3.1f%%" % (100.0*supportedTotal/len(name2unicode_AGD)))
print("\nRange processors not needed for AGD:")
for n in notNeeded:
print("\t", n)
def generateFlat(path, onlySupported=True, scriptSeparator=None, scriptAsPrefix=None, status=0, includeUnicodeCategory=False):
data = [
"# Glyph Name Formatted Unicode List - GNFUL",
"# GlyphNameFormatter version %s" % _versionNumber,
"# Unicode version: %s" % unicodeVersion,
"# Source code: %s" % _githubLink,
"# Generated on %s" % time.strftime("%Y %m %d %H:%M:%S"),
]
if includeUnicodeCategory:
data.append("# <glyphName> <hex unicode> <unicodeCategory>")
else:
data.append("# <glyphName> <hex unicode>")
if scriptSeparator is not None:
data.append("# Separator \"%s\"" % scriptSeparator)
if scriptAsPrefix is not None:
data.append("# Prefixed \"%s\"" % scriptAsPrefix)
data.append("#")
for rangeName in getAllRangeNames():
if onlySupported:
moduleName = rangeNameToModuleName(rangeName)
try:
module = importlib.import_module('glyphNameFormatter.rangeProcessors.%s' % moduleName)
except:
continue
data.append("# %s" % rangeName)
start, end = getRangeByName(rangeName)
for u in range(start, end+1):
g = GlyphName(uniNumber=u, scriptSeparator=scriptSeparator, scriptAsPrefix=scriptAsPrefix)
g.compress() # should auto compress
if status is not None:
if g.status < status:
# if the glyph has a status that is less than what we're looking for
# then do not include it in the list.
continue
name = g.getName(extension=True)
if name is None:
continue
if includeUnicodeCategory:
data.append("%s %04X %s" % (name, u, unicodeCategories.get(u, "-")))
else:
data.append("%s %04X" % (name, u))
f = open(path, "w")
f.write("\n".join(data))
f.close()
def generateFlat(path, onlySupported=True):
data = [
"# format",
"# <glyphName> <hex unicode>"
]
for rangeName in getAllRangeNames():
if onlySupported:
moduleName = rangeNameToModuleName(rangeName)
try:
module = importlib.import_module('glyphNameFormatter.rangeProcessors.%s' % moduleName)
except:
continue
data.append("# %s" % rangeName)
for u in range(*getRangeByName(rangeName)):
g = GlyphName(uniNumber=u)
name = g.getName(extension=True)
if name is None:
continue
data.append("%s %04X" % (name, u))
f = open(path, "w")
f.write("\n".join(data))
f.close()
# copy the latest name list
srcNamePath = os.path.join(
gnfRoot, "names", "glyphNamesToUnicodeAndCategories_experimental.txt")
if os.path.exists(srcNamePath):
dstNamePth = os.path.join(browserRoot, "data", "glyphNamesToUnicode.txt")
print "srcNamePath", srcNamePath
print "dstNamePth", dstNamePth
shutil.copyfile(srcNamePath, dstNamePth)
# make a range name table
from glyphNameFormatter.unicodeRangeNames import getAllRangeNames, getRangeByName
ranges = {}
for rangeName in getAllRangeNames():
r = getRangeByName(rangeName)
if r is None:
print("unknown range name", rangeName)
continue
start, end = r
ranges[(start, end)] = rangeName
pyText = []
pyText.append(u"# -*- coding: UTF-8 -*-")
pyText.append(u"# Generated from glyphNameFormatter range names")
pyText.append(u"# Generated on %s" % time.strftime("%Y %m %d %H:%M:%S"))
pyText.append(u"unicodeRangeNames =" + pprint.pformat(ranges, indent=4))
pyPath = os.path.join(browserRoot, "unicodeRanges.py")
print "pyPath", pyPath
# copy the joining types
srcJoiningTypesPath = os.path.join(gnfRoot, "data", "joiningTypes.txt")
if os.path.exists(srcJoiningTypesPath):
dstJoiningTypesPath = os.path.join(browserRoot, "data", "joiningTypes.txt")
print("srcJoiningTypesPath", srcJoiningTypesPath)
print("dstJoiningTypesPath", dstJoiningTypesPath)
shutil.copyfile(srcJoiningTypesPath, dstJoiningTypesPath)
# make a range name table
from glyphNameFormatter.unicodeRangeNames import getAllRangeNames, getRangeByName
ranges = {}
for rangeName in getAllRangeNames():
r = getRangeByName(rangeName)
if r is None:
print("unknown range name", rangeName)
continue
start, end = r
ranges[(start,end)] = rangeName
pyText = []
pyText.append(u"# -*- coding: UTF-8 -*-")
pyText.append(u"# Generated from glyphNameFormatter range names")
pyText.append(u"# Generated on %s" % time.strftime("%Y %m %d %H:%M:%S"))
pyText.append(u"unicodeRangeNames =" + pprint.pformat(ranges, indent=4))
pyPath = os.path.join(browserRoot, "unicodeRanges.py")
print("pyPath", pyPath)
def findConflict(makeModule=True, makeReport=False, printReport=False):
names = {}
dontReport = [
'tang:tangutideograph#',
'cjk:cjkunifiedideograph#',
'cjk:cjkcompatibilityideograph#',
'nsh:nushucharacter#',
'tangutideograph#',
'cjkunifiedideograph#',
'cjkcompatibilityideograph#',
'nushucharacter#',
]
#extendedNames = {}
lines = []
for rangeName in getAllRangeNames():
start, end = getRangeByName(rangeName)
for uniNumber in range(start, end + 1):
glyphName = glyphNameFormatter.GlyphName(uniNumber,
ignoreConflicts=True)
if glyphName.hasName():
# name = glyphName.getName(extension=False)
name = glyphName.getName(extension=True)
if name not in names:
names[name] = []
names[name].append(glyphName)
n = list(names.keys())
n.sort()
conflictNames = []
conflictUniNumbers = []
conflictsPerRange = {}
if makeReport:
line = "{0:>6s} | {1:<50}{2:<25}{3:<40}{4:<40}{5:<20}".format(
"hex", "basic formatted name", "AGL name", "with extension",
"range", "uni name")
if printReport:
print(line)
lines.append(line)
line = "{0:->6s} + {1:-<50}{2:-<25}{3:-<40}{4:-<40}{5:-<20}".format(
"", "", "+", "+", "+", "+")
if printReport:
print(line)
lines.append(line)
for name in n:
if len(names[name]) > 1:
conflictNames.append(name, )
line = ""
if printReport:
print()
lines.append(line)
for g in names[name]:
rangeName = g.uniRangeName
extendedName = g.getName(extension=True)
AGLname = unicode2name_AGD.get(g.uniNumber, "-")
nn = g.getName()
if nn in dontReport:
continue
conflictUniNumbers.append(g.uniNumber)
if makeReport:
line = "{0:>6X} : {1:<50}{2:<25}{3:<40}{4:<40}{5:<20}".format(
g.uniNumber, nn, AGLname[:25], g.getName(),
g.uniRangeName[:40], g.uniName)
if printReport:
print(line)
lines.append(line)
if rangeName not in conflictsPerRange:
conflictsPerRange[rangeName] = []
conflictsPerRange[rangeName].append(line)
if makeReport:
stats = "# %d names with conflicts, affecting %d unicodes" % (
len(conflictNames), len(conflictUniNumbers))
if printReport:
print(stats)
lines.append(stats)
dirName = os.path.dirname(__file__)
k = list(conflictsPerRange.keys())
if makeReport:
lines.append("")
lines.append("")
lines.append("Conflicts by rangename")
k.sort()
for rangeName in k:
lines.append("\n%s" % rangeName)
for line in conflictsPerRange[rangeName]:
lines.append(line)
path = os.path.join(dirName, "..", "data", "conflict.txt")
f = open(path, 'w')
f.write("\n".join(lines))
f.close()
# separate report for conflicts per range name
for rangeName in k:
rlines = []
for line in conflictsPerRange[rangeName]:
rlines.append(line)
d = os.path.join(dirName, "..", "data", "conflicts")
if not os.path.exists(d):
# remove it first
shutil.rmtree(d)
os.makedirs(d)
path = os.path.join(
dirName, "..", "data", "conflicts",
"conflict_%s.txt" % rangeName.replace(" ", "_").lower())
f = open(path, 'w')
f.write("\n".join(rlines))
f.close()
if makeModule:
path = os.path.join(dirName, "..", "data", "scriptConflictNames.py")
pyText = [
"# Table with conflicting names. Generated by /exporters/analyseConflicts.py",
"\nscriptConflictNames = ["
]
conflictNames.sort()
for name in conflictNames:
pyText.append(" \"%s\"," % name)
pyText.append("]\n\n")
f = open(path, 'w')
f.write("\n".join(pyText))
f.close()
def findConflict():
names = {}
lines = []
for rangeName in getAllRangeNames():
start, end = getRangeByName(rangeName)
for uniNumber in range(start, end+1):
glyphName = glyphNameFormatter.GlyphName(uniNumber)
if glyphName.hasName():
# lines.append("%04X\t%s\t%s" % (uniNumber, glyphName.getName(), glyphName.uniName))
name = glyphName.getName(extension=False)
extendedName = glyphName.getName(extension=True)
if not name in names:
names[name] = []
names[name].append(glyphName)
n = names.keys()
n.sort()
conflictNames = []
conflictUniNumbers = []
conflictsPerRange = {}
line = "{0:>6s} | {1:<50}{2:<25}{3:<40}{4:<40}".format("hex", "basic formatted name", "AGL name", "with extension", "range")
print(line)
lines.append(line)
line = "{0:->6s} + {1:-<50}{2:-<25}{3:-<40}{4:<40}".format("", "", "+", "+", "+")
print(line)
lines.append(line)
for name in n:
if len(names[name]) > 1:
conflictNames.append(name)
line = ""
print()
lines.append(line)
for g in names[name]:
rangeName = g.uniRangeName
extendedName = g.getName(extension=True)
conflictUniNumbers.append(g.uniNumber)
AGLname = unicode2name_AGD.get(g.uniNumber, "-")
line = "{0:>6X} : {1:<50}{2:<25}{3:<40}{4:<40}".format(g.uniNumber, g.getName(), AGLname[:25], g.getName(), g.uniRangeName[:40])
print(line)
lines.append(line)
if not rangeName in conflictsPerRange:
conflictsPerRange[rangeName] = []
conflictsPerRange[rangeName].append(line)
stats = "# %d names with conflicts, affecting %d unicodes"%(len(conflictNames), len(conflictUniNumbers))
print(stats)
lines.append(stats)
k = conflictsPerRange.keys()
lines.append("")
lines.append("")
lines.append("Conflicts by rangename")
k.sort()
for rangeName in k:
lines.append("\n%s"%rangeName)
for line in conflictsPerRange[rangeName]:
lines.append(line)
path = "./../names/conflict.txt"
f = open(path, 'w')
f.write("\n".join(lines))
f.close()
path = "./../data/scriptConflictNames.py"
pyText = ["# Table with conflicting names. Generated by /test/testConflicts.py", "\nscriptConflictNames = ["]
conflictNames.sort()
for name in conflictNames:
pyText.append(" \"%s\","%name)
pyText.append("]\n\n")
f = open(path, 'w')
f.write("\n".join(pyText))
f.close()
def testCoverage():
uncountables = [
'Hangul Syllables',
'CJK Unified Ideographs',
'Private'
]
uncounted = []
text = []
text.append("\n\n# Coverage")
wantRanges = {}
glyphCount = {}
for thisRange in getAllRangeNames():
a, b = getRangeByName(thisRange)
countThis = True
for uc in uncountables:
if thisRange.find(uc)!=-1:
uncounted.append(" * %s"%thisRange)
print(thisRange, "uncountable")
countThis = False
moduleName = rangeNameToModuleName(thisRange)
if thisRange not in glyphCount:
glyphCount[thisRange] = {'nameable': 0, 'uniNames':0, 'total':b-a, 'rangeProcessor':None}
try:
module = importlib.import_module('glyphNameFormatter.rangeProcessors.%s' % moduleName)
glyphCount[thisRange]['rangeProcessor']=True
except ImportError:
pass
for uniNumber in range(a,b):
g = GlyphName(uniNumber)
if g.uniName is not None:
glyphCount[thisRange]['uniNames'] += 1
if countThis:
glyphCount[thisRange]['nameable'] += 1
totalGlyphs = 0 # the total of all glyph counts in all ranges
totalCovered = 0 # the total of all glyphs that this package has rangeprocessors for
totalPoints = 0 # the total of all ranges
totalNameable = 0 # the total of all glyphs that can be named
for key, items in glyphCount.items():
#print(key, items)
totalGlyphs += items['uniNames']
totalPoints += items['total']
if items['rangeProcessor'] is not None:
totalCovered += items['uniNames']
totalNameable += items['nameable']
text = []
text.append("")
text.append("## Version %s"%unicodeVersion)
text.append("\n\n\n")
text.append("This coverage page is has some issues.")
text.append(" * The version of python used to build the table does not have the latest Unicode data.")
text.append(" * Narrow build Python might also leave some names inaccessible.")
text.append(" * Not all ranges need to count. Private Use ranges are ignored, perhaps others need to as well.")
text.append("\n\n\n")
# if uncounted:
# text.append("The following ranges are skipped:")
# for line in uncounted:
# text.append(line)
# text.append("\n\n\n")
# text.append("| Stats | :) |")
# text.append("| ------------------------------------------ | --------: |")
# text.append('| Total code points in the available ranges | `%d` |'%totalPoints)
# text.append('| Total glyphs in the available ranges | `%d` |'%totalGlyphs)
# text.append('| Total glyphs that can be named | `%d` |'%totalNameable)
# text.append('| Total names covered in GlyphNameFormatter | `%d` |'%totalCovered)
# text.append('| Progress | `%3.3f%%` |'%(100.0*totalCovered/totalGlyphs))
text.append("\n\n\n")
text.append("| Range name | # | has processor | Start | End |")
text.append("| ----- | ----- |----- | ----- | ----- |")
for thisRange in getAllRangeNames():
if not thisRange in glyphCount: continue
a, b = getRangeByName(thisRange)
items = glyphCount[thisRange]
if items['rangeProcessor']!=None:
has = "**Yes**"
n = "**%s**"%items['uniNames']
else:
has = "No"
n = items['uniNames']
text.append("| %s | %s | %s | `%04X` | `%04X` |"%(thisRange, n, has, a, b))
text.append("\n\n")
path = "../../../coverage.md"
f = open(path, 'w')
f.write("\n".join(text))
f.close()
def findConflict(makeModule=True, makeReport=False, printReport=False):
names = {}
lines = []
for rangeName in getAllRangeNames():
start, end = getRangeByName(rangeName)
for uniNumber in range(start, end+1):
glyphName = glyphNameFormatter.GlyphName(uniNumber)
if glyphName.hasName():
name = glyphName.getName(extension=False)
extendedName = glyphName.getName(extension=True)
if name not in names:
names[name] = []
names[name].append(glyphName)
n = names.keys()
n.sort()
conflictNames = []
conflictUniNumbers = []
conflictsPerRange = {}
if makeReport:
line = "{0:>6s} | {1:<50}{2:<25}{3:<40}{4:<40}{5:<20}".format("hex", "basic formatted name", "AGL name", "with extension", "range", "uni name")
if printReport:
print(line)
lines.append(line)
line = "{0:->6s} + {1:-<50}{2:-<25}{3:-<40}{4:-<40}{5:-<20}".format("", "", "+", "+", "+", "+")
if printReport:
print(line)
lines.append(line)
for name in n:
if len(names[name]) > 1:
conflictNames.append(name)
line = ""
if printReport:
print()
lines.append(line)
for g in names[name]:
rangeName = g.uniRangeName
extendedName = g.getName(extension=True)
conflictUniNumbers.append(g.uniNumber)
AGLname = unicode2name_AGD.get(g.uniNumber, "-")
if makeReport:
line = "{0:>6X} : {1:<50}{2:<25}{3:<40}{4:<40}{5:<20}".format(g.uniNumber, g.getName(), AGLname[:25], g.getName(), g.uniRangeName[:40], g.uniName)
if printReport:
print(line)
lines.append(line)
if rangeName not in conflictsPerRange:
conflictsPerRange[rangeName] = []
conflictsPerRange[rangeName].append(line)
if makeReport:
stats = "# %d names with conflicts, affecting %d unicodes" % (len(conflictNames), len(conflictUniNumbers))
if printReport:
print(stats)
lines.append(stats)
dirName = os.path.dirname(__file__)
k = conflictsPerRange.keys()
if makeReport:
lines.append("")
lines.append("")
lines.append("Conflicts by rangename")
k.sort()
for rangeName in k:
lines.append("\n%s" % rangeName)
for line in conflictsPerRange[rangeName]:
lines.append(line)
path = os.path.join(dirName, "..", "data", "conflict.txt")
f = open(path, 'w')
f.write("\n".join(lines))
f.close()
if makeModule:
path = os.path.join(dirName, "..", "data", "scriptConflictNames.py")
pyText = ["# Table with conflicting names. Generated by /test/testConflicts.py", "\nscriptConflictNames = ["]
conflictNames.sort()
for name in conflictNames:
pyText.append(" \"%s\"," % name)
pyText.append("]\n\n")
f = open(path, 'w')
f.write("\n".join(pyText))
f.close()
def findConflict(makeModule=True, makeReport=False, printReport=False):
names = {}
dontReport = [
'tang:tangutideograph#',
'cjk:cjkunifiedideograph#',
'cjk:cjkcompatibilityideograph#',
'nsh:nushucharacter#',
'tangutideograph#',
'cjkunifiedideograph#',
'cjkcompatibilityideograph#',
'nushucharacter#',
]
#extendedNames = {}
lines = []
for rangeName in getAllRangeNames():
start, end = getRangeByName(rangeName)
for uniNumber in range(start, end+1):
glyphName = glyphNameFormatter.GlyphName(uniNumber, ignoreConflicts=True)
if glyphName.hasName():
# name = glyphName.getName(extension=False)
name = glyphName.getName(extension=True)
if name not in names:
names[name] = []
names[name].append(glyphName)
n = list(names.keys())
n.sort()
conflictNames = []
conflictUniNumbers = []
conflictsPerRange = {}
if makeReport:
line = "{0:>6s} | {1:<50}{2:<25}{3:<40}{4:<40}{5:<20}".format("hex", "basic formatted name", "AGL name", "with extension", "range", "uni name")
if printReport:
print(line)
lines.append(line)
line = "{0:->6s} + {1:-<50}{2:-<25}{3:-<40}{4:-<40}{5:-<20}".format("", "", "+", "+", "+", "+")
if printReport:
print(line)
lines.append(line)
for name in n:
if len(names[name]) > 1:
conflictNames.append(name, )
line = ""
if printReport:
print()
lines.append(line)
for g in names[name]:
rangeName = g.uniRangeName
extendedName = g.getName(extension=True)
AGLname = unicode2name_AGD.get(g.uniNumber, "-")
nn = g.getName()
if nn in dontReport:
continue
conflictUniNumbers.append(g.uniNumber)
if makeReport:
line = "{0:>6X} : {1:<50}{2:<25}{3:<40}{4:<40}{5:<20}".format(g.uniNumber, nn, AGLname[:25], g.getName(), g.uniRangeName[:40], g.uniName)
if printReport:
print(line)
lines.append(line)
if rangeName not in conflictsPerRange:
conflictsPerRange[rangeName] = []
conflictsPerRange[rangeName].append(line)
if makeReport:
stats = "# %d names with conflicts, affecting %d unicodes" % (len(conflictNames), len(conflictUniNumbers))
if printReport:
print(stats)
lines.append(stats)
dirName = os.path.dirname(__file__)
k = list(conflictsPerRange.keys())
if makeReport:
lines.append("")
lines.append("")
lines.append("Conflicts by rangename")
k.sort()
for rangeName in k:
lines.append("\n%s" % rangeName)
for line in conflictsPerRange[rangeName]:
lines.append(line)
path = os.path.join(dirName, "..", "data", "conflict.txt")
f = open(path, 'w')
f.write("\n".join(lines))
f.close()
# separate report for conflicts per range name
for rangeName in k:
rlines = []
for line in conflictsPerRange[rangeName]:
rlines.append(line)
d = os.path.join(dirName, "..", "data", "conflicts")
if not os.path.exists(d):
# remove it first
shutil.rmtree(d)
os.makedirs(d)
path = os.path.join(dirName, "..", "data", "conflicts", "conflict_%s.txt" % rangeName.replace(" ", "_").lower() )
f = open(path, 'w')
f.write("\n".join(rlines))
f.close()
if makeModule:
path = os.path.join(dirName, "..", "data", "scriptConflictNames.py")
pyText = ["# Table with conflicting names. Generated by /exporters/analyseConflicts.py", "\nscriptConflictNames = ["]
conflictNames.sort()
for name in conflictNames:
pyText.append(" \"%s\"," % name)
pyText.append("]\n\n")
f = open(path, 'w')
f.write("\n".join(pyText))
f.close()
def testCoverage():
uncountables = ['Hangul Syllables', 'CJK Unified Ideographs', 'Private']
uncounted = []
text = []
text.append("\n\n# Coverage")
wantRanges = {}
glyphCount = {}
for thisRange in getAllRangeNames():
a, b = getRangeByName(thisRange)
countThis = True
for uc in uncountables:
if thisRange.find(uc) != -1:
uncounted.append(" * %s" % thisRange)
print(thisRange, "uncountable")
countThis = False
moduleName = rangeNameToModuleName(thisRange)
if thisRange not in glyphCount:
glyphCount[thisRange] = {
'nameable': 0,
'uniNames': 0,
'total': b - a,
'rangeProcessor': None
}
try:
module = importlib.import_module(
'glyphNameFormatter.rangeProcessors.%s' % moduleName)
glyphCount[thisRange]['rangeProcessor'] = True
except ImportError:
pass
for uniNumber in range(a, b):
g = GlyphName(uniNumber)
if g.uniName is not None:
glyphCount[thisRange]['uniNames'] += 1
if countThis:
glyphCount[thisRange]['nameable'] += 1
totalGlyphs = 0 # the total of all glyph counts in all ranges
totalCovered = 0 # the total of all glyphs that this package has rangeprocessors for
totalPoints = 0 # the total of all ranges
totalNameable = 0 # the total of all glyphs that can be named
for key, items in glyphCount.items():
#print(key, items)
totalGlyphs += items['uniNames']
totalPoints += items['total']
if items['rangeProcessor'] is not None:
totalCovered += items['uniNames']
totalNameable += items['nameable']
text = []
text.append("")
text.append("## Version %s" % unicodeVersion)
text.append("\n\n\n")
text.append("### Note:\n")
text.append("This coverage page is has some issues.\n")
text.append(
" * Most of the Unicode data is downloaded from Unicode.org. Only the bidirectional data still depends on the Python unicodedata module.."
)
text.append(
" * Narrow build Python might also leave some names inaccessible.")
text.append(
" * Not all ranges need to count. Private Use ranges are ignored, perhaps others need to as well."
)
text.append("\n\n\n")
# if uncounted:
# text.append("The following ranges are skipped:")
# for line in uncounted:
# text.append(line)
# text.append("\n\n\n")
# text.append("| Stats | :) |")
# text.append("| ------------------------------------------ | --------: |")
# text.append('| Total code points in the available ranges | `%d` |'%totalPoints)
# text.append('| Total glyphs in the available ranges | `%d` |'%totalGlyphs)
# text.append('| Total glyphs that can be named | `%d` |'%totalNameable)
# text.append('| Total names covered in GlyphNameFormatter | `%d` |'%totalCovered)
# text.append('| Progress | `%3.3f%%` |'%(100.0*totalCovered/totalGlyphs))
text.append("\n\n\n")
text.append("| Range name | # | has processor | Start | End |")
text.append("| ----- | ----- |----- | ----- | ----- |")
for thisRange in getAllRangeNames():
if not thisRange in glyphCount: continue
a, b = getRangeByName(thisRange)
items = glyphCount[thisRange]
if items['rangeProcessor'] != None:
has = "**Yes**"
n = "**%s**" % items['uniNames']
else:
has = "No"
n = items['uniNames']
text.append("| %s | %s | %s | `%04X` | `%04X` |" %
(thisRange, n, has, a, b))
text.append("\n\n")
path = "../../../coverage.md"
f = open(path, 'w')
f.write("\n".join(text))
f.close()