option to include bitmaps to metrics and generate_pbff outputs

.gitignore

@@ -1,2 +1,4 @@
 __pycache__/
 *.pyc
+
+out/

generate_pbff.py

@@ -43,6 +43,10 @@ def generate_pbff_file(data, out):
         (top, left, advance, width, height, codepoint) = \
             (glyph[x] for x in
              ('top', 'left', 'advance', 'width', 'height', 'codepoint'))
+        try:
+            glyph_bitmap_bits = glyph['bits']
+        except KeyError:
+            glyph_bitmap_bits = []
 
         print('glyph %d%s' % (
             codepoint,
@@ -56,10 +60,23 @@ def generate_pbff_file(data, out):
             print('.')
         print(' %d' % top, file=out)
 
-        for x in range(height):
+        glyph_bitmap_bits_offset = 0
+        for y in range(height):
             if left > 0:
                 print(' ' * left, end='', file=out)
-            print('#' * width, file=out)
+            if glyph_bitmap_bits:
+                for x in range(width):
+                    letter = ' '
+                    try:
+                        if glyph_bitmap_bits[glyph_bitmap_bits_offset] >= 1:
+                            letter = '#'
+                    except IndexError:
+                        pass
+                    glyph_bitmap_bits_offset += 1
+                    print(letter, end='', file=out)
+                print(end='\n', file=out)
+            else:
+                print('#' * width, file=out)
 
         print('-', file=out)
 

metrics.py

@@ -4,12 +4,13 @@
 ###############################################################################
 #                                                                             #
 #              Reads font files and outputs metrics json data                 #
-#                     file based on the font metrics.                         #
+#         file based on the font metrics. Can include bitmaps bits.           #
 #                                                                             #
 ###############################################################################
 
 import argparse
 import json
+import math
 import os.path
 import struct
 import sys
@@ -62,6 +63,24 @@ def read_all(self):
 
 
 class FontReader:
+    def __init__(self, include_bitmaps):
+        if include_bitmaps:
+            print('Bitmaps inclusion enabled')
+            self.include_bitmaps = True
+        else:
+            print('Bitmaps inclusion disabled')
+            self.include_bitmaps = False
+
+    def get_bits_no_padding(self, bytes_iter: bytes, original_length: int) -> list[int]:
+        bits: list[int] = []
+        for byte in bytes_iter:
+            byte_bits: list[int] = []
+            byte_str = format(byte, '08b')
+            for bit_str in byte_str:
+                byte_bits.append(int(bit_str))
+            bits.extend(reversed(byte_bits))
+        return bits[:original_length]
+
     # The actual font reader.
     def read(self, fh):
         fh = FileReader(fh)
@@ -80,10 +99,13 @@ def read(self, fh):
         size = None
         features = 0
 
-        if version >= 2:
-            (hash_table_size,  # B
-             codepoint_bytes   # B
-             ) = struct.unpack('<BB', fh.read(2))
+        if version <= 1:
+            raise Exception(f'font version {version} not supported')
+
+        # if version >= 2:
+        (hash_table_size,  # B
+         codepoint_bytes   # B
+         ) = struct.unpack('<BB', fh.read(2))
 
         if version >= 3:
             (size,     # B
@@ -119,9 +141,10 @@ def read(self, fh):
         glyph_table_data = []
 
         for offset_list in offset_table_data:
+            # This check can be commented out if a font file raises this exception
             if (offset_list['offset'] !=
-                    fh.bytes_read - first_offset_item_offset):
-                raise Exception('Offset item at incorrect offset')
+                   fh.bytes_read - first_offset_item_offset):
+               raise Exception('Offset item at incorrect offset')
             for codepoint_index in range(offset_list['size']):
                 (codepoint,  # B or H, depending on codepoint_bytes
                  offset      # B or H, depending on features
@@ -149,14 +172,23 @@ def read(self, fh):
              left,
              top,
              advance) = struct.unpack(
-                '<BBbbbxxx', glyph_data[glyph['offset']:glyph['offset'] + 8])
+                '<BBbbb', glyph_data[glyph['offset']:glyph['offset'] + 5]) # 5 is header size
+
+            if self.include_bitmaps:
+                glyph_bitmap_data_size: int = math.ceil((width * height) / 8)
+                glyph_bitmap_data = glyph_data[glyph['offset'] + 5:glyph['offset'] + 5 + glyph_bitmap_data_size]
+                glyph_bitmap_bits = self.get_bits_no_padding(glyph_bitmap_data, width * height)
+            else:
+                glyph_bitmap_bits = []
+
             glyph_list += [{'character': chr(glyph['codepoint']),
                             'codepoint': glyph['codepoint'],
                             'width': width,
                             'height': height,
                             'left': left,
                             'top': top,
-                            'advance': advance}]
+                            'advance': advance,
+                            'bits': glyph_bitmap_bits}]
 
         # ----------------------------------------------------------------------
 
@@ -170,15 +202,24 @@ def read(self, fh):
 
 if __name__ == '__main__':
     parser = argparse.ArgumentParser()
-    parser.add_argument('files', nargs='+',
+    parser.add_argument('files',
+                        nargs='+',
                         help='files to be parsed')
+    parser.add_argument('-ib', '--include-bitmaps', 
+                        action='store_true',
+                        help='add to include glyphs bitmap bits in output json')
     a = parser.parse_args()
-    data = {}
+
+    if not os.path.isdir('out'):
+        os.mkdir('out')
+
     for f in a.files:
-        with open(f, 'rb') as fh:
-            r = FontReader()
-            if (os.path.split(f)[-1]) in data:
-                print('file named', os.path.split(f)[-1],
-                      'already processed; skipping')
-            data[os.path.split(f)[-1]] = r.read(fh)
-    json.dump(data, sys.stdout, indent=2)
+        data = {}
+        with open(f, 'rb') as fh,\
+            open(os.path.join('out', f'{f}.metrics.json'), 'w', encoding='utf-8') as out:
+                r = FontReader(a.include_bitmaps)
+                if (os.path.split(f)[-1]) in data:
+                    print('file named', os.path.split(f)[-1],
+                        'already processed; skipping')
+                data[os.path.split(f)[-1]] = r.read(fh)
+                json.dump(data, out, indent=2, ensure_ascii=False)