Initial commit: RE tooling and docs for The I of the Dragon localization/HD

tools/fontparse.py

@@ -0,0 +1,81 @@
+import re, os
+
+txt = open(r"C:\Users\29452\AppData\Local\Temp\opencode\decoded\Fonts.dat.txt", encoding="latin1").read()
+
+# tokenize blocks
+def parse_block(s, i):
+    # s[i] should be at '{'
+    assert s[i] == '{'
+    i += 1
+    entries = []  # (name, value, childidx)
+    children = []
+    cur_name = None
+    while i < len(s):
+        # skip whitespace
+        while i < len(s) and s[i] in ' \t\r\n':
+            i += 1
+        if i >= len(s):
+            break
+        if s[i] == '}':
+            return entries, i+1
+        # read a name
+        m = re.match(r'[A-Za-z_#][A-Za-z0-9_#]*', s[i:])
+        if m:
+            name = m.group(0)
+            i += len(name)
+            while i < len(s) and s[i] in ' \t\r\n':
+                i += 1
+            if i < len(s) and s[i] == '=':
+                i += 1
+                while i < len(s) and s[i] in ' \t\r\n':
+                    i += 1
+                if i < len(s) and s[i] == '"':
+                    j = i+1
+                    while j < len(s) and s[j] != '"':
+                        j += 1
+                    val = s[i+1:j]
+                    i = j+1
+                else:
+                    m2 = re.match(r'[^\s{}]+', s[i:])
+                    val = m2.group(0) if m2 else ''
+                    i += len(val)
+                entries.append((name, val))
+            elif i < len(s) and s[i] == '{':
+                sub, i = parse_block(s, i)
+                children.append((name, sub))
+                entries.append((name, sub))
+            else:
+                entries.append((name, ''))
+        else:
+            i += 1
+    return entries, i
+
+# find top-level Font blocks
+blocks = []
+for m in re.finditer(r'\bFont\b\s*\{', txt):
+    start = txt.index('{', m.start())
+    ent, _ = parse_block(txt, start)
+    blocks.append(ent)
+
+print("num Font blocks:", len(blocks))
+for b in blocks:
+    d = dict((k, v) for k, v in b if k in ('Name','Language','Texture','#Texture','SpaceWidth','LineDistance','CharDistance'))
+    langs = [v for k, v in b if k == 'Language']
+    texs = [v for k, v in b if k in ('Texture', '#Texture')]
+    chars = [c for k, c in b if k == 'Char']
+    print("Font Name=%s langs=%s textures=%s #char=%d" % (d.get('Name'), langs, texs, len(chars)))
+
+# print rect for 'e' in first block
+def charmap(block):
+    cm = {}
+    for k, c in block:
+        if k == 'Char':
+            cd = dict((k2, v2) for k2, v2 in c)
+            cm[cd.get('Code')] = (int(cd.get('X1',0)), int(cd.get('Y1',0)), int(cd.get('X2',0)), int(cd.get('Y2',0)))
+    return cm
+
+for bi, b in enumerate(blocks):
+    cm = charmap(b)
+    for ch in ['e','a','o','A',' ']:
+        if ch in cm:
+            print(f"block{bi} '{ch}' -> {cm[ch]}")