From 72e513e9c0f58cd676016f0980ae61505e8da3dd Mon Sep 17 00:00:00 2001
From: Richard Wheeler <2762690+zephyris@users.noreply.github.com>
Date: Fri, 1 Mar 2024 23:56:52 +0000
Subject: [PATCH] Add: Script to check character coverage against OpenTTD
 translations

Also adds running this script to the build process; assumes the OpenTTD source exists in `../openttd`.
---
 build.sh               |  2 ++
 checkOpenTTDStrings.py | 67 ++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 69 insertions(+)
 create mode 100644 checkOpenTTDStrings.py

diff --git a/build.sh b/build.sh
index 40342b5..95f195a 100644
--- a/build.sh
+++ b/build.sh
@@ -15,3 +15,5 @@ cd ..
 cd openttd-mono
 bash build.sh
 cd ..
+
+python3 checkOpenTTDStrings.py ../openttd/src/lang
diff --git a/checkOpenTTDStrings.py b/checkOpenTTDStrings.py
new file mode 100644
index 0000000..98ee632
--- /dev/null
+++ b/checkOpenTTDStrings.py
@@ -0,0 +1,67 @@
+#!/usr/bin/python3
+
+# Checks characters used in OpenTTD strings against characters present in these fonts
+
+# Usage:
+# python3 checkTranslationChars.py path/to/openttd/src/lang
+# python3 path/to/checkTranslationChars.py [run in openttd/src/lang]
+
+import glob, os, sys
+from fontTools.ttLib import TTFont
+
+if len(sys.argv) > 1:
+  langpath = sys.argv[1]
+else:
+  langpath = "."
+
+# maximum number of missing characters to list in full
+maxlist = 100
+
+# find all ttfs by suffix in directory
+suffix = ".ttf"
+scriptpath = os.path.dirname(os.path.realpath(__file__))
+files = [
+  os.path.join(scriptpath, "openttd-sans", "OpenTTD-Sans.ttf"),
+  os.path.join(scriptpath, "openttd-serif", "OpenTTD-Serif.ttf"),
+  os.path.join(scriptpath, "openttd-mono", "OpenTTD-Mono.ttf"),
+  os.path.join(scriptpath, "openttd-small", "OpenTTD-Small.ttf"),
+  os.path.join(scriptpath, "openttd-small", "OpenTTD-SmallCaps.ttf")
+]
+fonts = []
+for file in files:
+  # for each font, record name and list of character codes available
+  font = TTFont(file)
+  fonts.append({
+    "name": os.path.basename(file[:-len(suffix)]),
+    "codes": list(font.getBestCmap().keys())
+  })
+
+# find all lang files by suffix in directory
+suffix = ".txt"
+files = glob.glob(os.path.join(langpath, "*" + suffix))
+print(os.path.join(langpath, "*" + suffix))
+for file in files:
+  # for each language
+  lang = os.path.basename(file[:-len(suffix)])
+  with open(file, "r") as handle:
+    # read lines and remove empty lines
+    strings = [x for x in handle.read().splitlines() if x]
+    # extract translated strings
+    strings = [x[x.find(":") + 1:] for x in strings if x[0] != "#"]
+    # list all character codes and characters across strings
+    codes = sorted(list(set([ord(x) for x in "".join(strings)])))
+    chars = [chr(x) for x in codes]
+    # check if fully supported by each font
+    print(lang)
+    completecount = 0
+    for font in fonts:
+      missing = [x for x in codes if x not in font["codes"]]
+      if len(missing) == 0:
+        completecount += 1
+      else:
+        if len(missing) <= maxlist:
+          print("", font["name"], "missing "+str(len(missing))+":", "("+"".join([chr(x) for x in missing])+")")
+        else:
+          print("", font["name"], "missing "+str(len(missing))+":", "[too many to list]")
+    if completecount == len(fonts):
+      print("", "[complete]")
\ No newline at end of file