-
-
Save pklaus/dce37521579513c574d0 to your computer and use it in GitHub Desktop.
| #!/usr/bin/env python | |
| """ | |
| From | |
| https://github.com/gddc/ttfquery/blob/master/ttfquery/describe.py | |
| and | |
| http://www.starrhorne.com/2012/01/18/how-to-extract-font-names-from-ttf-files-using-python-and-our-old-friend-the-command-line.html | |
| ported to Python 3 | |
| """ | |
| import sys | |
| from fontTools import ttLib | |
| FONT_SPECIFIER_NAME_ID = 4 | |
| FONT_SPECIFIER_FAMILY_ID = 1 | |
| def shortName( font ): | |
| """Get the short name from the font's names table""" | |
| name = "" | |
| family = "" | |
| for record in font['name'].names: | |
| if b'\x00' in record.string: | |
| name_str = record.string.decode('utf-16-be') | |
| else: | |
| name_str = record.string.decode('utf-8') | |
| if record.nameID == FONT_SPECIFIER_NAME_ID and not name: | |
| name = name_str | |
| elif record.nameID == FONT_SPECIFIER_FAMILY_ID and not family: | |
| family = name_str | |
| if name and family: break | |
| return name, family | |
| tt = ttLib.TTFont(sys.argv[1]) | |
| print("Name: %s Family: %s" % shortName(tt)) |
Hello.
I used your script, but got error:
for record in font['name'].names:
TypeError: string indices must be integers
I'm using Python 3.7.4
Please help me to solve this problem because I have many ttf files that must know their names to choose which of them needs to install.
tnx a lot.
You have to call the function shortName() with the object that the call to ttLib.TTFont returns. It can be found in the package fonttolls (pip install fonttools). The object is of type fontTools.ttLib.ttFont.TTFont:
tt = ttLib.TTFont("DejaVuSansMono-Bold.ttf")
print("Name: %s Family: %s" % shortName(tt))
Name: DejaVu Sans Mono Bold Family: DejaVu Sans Mono
Hope that helps.
Can I use your code in my research project? Do you have a License requirement?
My research project will be published as open source as soon as it's ready.
python 3.8 (will work for lower versions too). requirements: pip3 install fonttools
import os
from contextlib import redirect_stderr
from fontTools import ttLib
def font_name(font_path):
font = ttLib.TTFont(font_path, ignoreDecompileErrors=True)
with redirect_stderr(None):
names = font['name'].names
details = {}
for x in names:
if x.langID == 0 or x.langID == 1033:
try:
details[x.nameID] = x.toUnicode()
except UnicodeDecodeError:
details[x.nameID] = x.string.decode(errors='ignore')
return details[4], details[1], details[2]
print(font_name('myfont.ttf')) # ('Century Bold Italic', 'Century', 'Bold Italic') – name, family, style
Can I use your code in my research project? Do you have a License requirement?
My research project will be published as open source as soon as it's ready.
you can use https://gist.github.com/pklaus/dce37521579513c574d0#gistcomment-3507444 its free
You should never try to decode fontname by yourself.
Here is how you should do it:
from fontTools import ttLib
font = ttLib.TTFont(fontPath)
fontFamilyName = font['name'].getDebugName(1)
fullName= font['name'].getDebugName(4)The number 1, 4 are nameID. If you need anything more, read this documentation about nameID: https://docs.microsoft.com/en-us/typography/opentype/spec/name#name-ids
Here is fonttools documentation about the naming table: https://fonttools.readthedocs.io/en/latest/ttLib/tables/_n_a_m_e.html
Great, but does not work with woff2 files
Great, but does not work with woff2 files
@tsastsin Could you share your woff2 files?
I don't know much about that font format, but I just test with an woff2 file and it work.
Also, have you try the method I wrote?
@moi15moi My mistake, sorry, the brotli installation was missing.
Now there are no problems with woff2 files.
Yes, I am using your method, thank you!
MIT License.
Here's a version that doesn't even need fonttools. It's also built for speed. We do not read any unneeded bytes or parse anything that isn't directly helping us find these values. In testing this parsed about 31 files per millisecond.
def query_name(filename):
def get_string(f, off, length):
string = None
try:
location = f.tell()
f.seek(off)
string = f.read(length)
f.seek(location)
return string.decode("UTF-16BE")
except UnicodeDecodeError:
try:
return string.decode("UTF8")
except UnicodeDecodeError:
return string
with open(filename, "rb") as f:
(
sfnt_version,
num_tables,
search_range,
entry_selector,
range_shift,
) = struct.unpack(">LHHHH", f.read(12))
name_table = False
for i in range(num_tables):
tag, checksum, offset, length = struct.unpack(">4sLLL", f.read(16))
if tag == b"name":
f.seek(offset)
name_table = True
break
if not name_table:
return None, None, None
# We are now at the name table.
table_start = f.tell()
(
fmt,
count,
strings_offset,
) = struct.unpack(">HHH", f.read(6))
if fmt == 1:
(langtag_count,) = struct.unpack(">H", f.read(2))
for langtag_record in range(langtag_count):
(langtag_len, langtag_offset) = struct.unpack(">HH", f.read(4))
font_family = None
font_subfamily = None
font_name = None
for record_index in range(count):
(
platform_id,
platform_specific_id,
language_id,
name_id,
length,
record_offset,
) = struct.unpack(">HHHHHH", f.read(2 * 6))
pos = table_start + strings_offset + record_offset
if name_id == 1:
font_family = get_string(f, pos, length)
elif name_id == 2:
font_family = get_string(f, pos, length)
elif name_id == 4:
font_name = get_string(f, pos, length)
if font_family and font_subfamily and font_name:
break
return font_family, font_subfamily, font_name
@tatarize If you really want to decode it by yourself, you should use the right encoding.
Here is what GDI (windows) does:
def get_name_encoding(name: NameRecord) -> Optional[str]:
"""
Parameters:
names (NameRecord): Name record from the naming record
Returns:
The cmap codepoint encoding.
If GDI does not support the name, return None.
"""
# From: https://github.com/MicrosoftDocs/typography-issues/issues/956#issuecomment-1205678068
if name.platformID == 3:
if name.platEncID == 3:
return "cp936"
elif name.platEncID == 4:
if name.nameID == 2:
return "utf_16_be"
else:
return "cp950"
elif name.platEncID == 5:
if name.nameID == 2:
return "utf_16_be"
else:
return "cp949"
else:
return "utf_16_be"
elif name.platformID == 1 and name.platEncID == 0:
return "iso-8859-1"
return None
@staticmethod
def get_decoded_name(name: NameRecord) -> str:
"""
Parameters:
names (NameRecord): Name record from the naming record
Returns:
The decoded name
"""
encoding = FontParser.get_name_encoding(name)
if name.platformID == 3 and encoding != "utf_16_be":
# Compatibility for really old font
name_to_decode = name.string.replace(b"\x00", b"")
else:
name_to_decode = name.string
return name_to_decode.decode(encoding)
Hello, I used your script, but got error:
Then I tryed this encoding (
.decode('latin-1'))
And it works good:
My system req: