[WebUI] Update gettext script to find any missed marked-up text

Added a new function to the gettext script that will check common
extjs attributes for missing markup text strings and print the result.

1 files changed, 59 insertions, 7 deletions

diff --git a/gen_web_gettext.py b/gen_web_gettext.py
index b9c1c734c..519edf7bd 100755
--- a/gen_web_gettext.py
+++ b/gen_web_gettext.py
@@ -20,19 +20,65 @@ WEBUI_JS_DIR = 'deluge/ui/web/js/deluge-all'
 DEBUG = False
 
 
-def create_gettext_js(js_dir):
-    string_re = re.compile('_\\(\'(.*?)\'\\)')
+def check_missing_markup(js_dir):
+    """Search js to check for missed translation markup."""
+
+    # A list of common extjs attributes that are usually marked for translation.
+    attr_list = [
+        "text: '",
+        "msg: '",
+        "title: '",
+        "fieldLabel: '",
+        "boxLabel: '",
+        "tooltip: '",
+        "header: '",
+        "defaultText: '",
+        "unit: '",
+        r"setText\('",
+        r"addButton\('",
+    ]
+
+    # Don't match against any of these chars at start of string value.
+    except_chars = "' &#"
+
+    # A list of strings that should be skipped shuold the match contain them.
+    skip = ["HTTP:"]
+
+    # Create a list of the matching strings to search for with the except_chars appended to each one.
+    string_re = re.compile(
+        "(" + ")|(".join(["%s[^" + except_chars + "].*'"]*len(attr_list)) % tuple(attr_list) + ")"
+    )
 
     strings = {}
     for root, dnames, files in os.walk(js_dir):
         for filename in files:
-            if os.path.splitext(filename)[1] == '.js':
-                for lineno, line in enumerate(open(os.path.join(root, filename))):
-                    for match in string_re.finditer(line):
-                        string = match.group(1)
+            if os.path.splitext(filename)[1] != '.js':
+                continue
+            for lineno, line in enumerate(open(os.path.join(root, filename))):
+                for match in string_re.finditer(line):
+                    for string in match.groups():
+                        # Ignore string that contains only digits or specificied strings in skip.
+                        if not string or string.split("'")[1].isdigit() or any(x in string for x in skip):
+                            continue
                         locations = strings.get(string, [])
-                        locations.append((os.path.basename(filename), lineno + 1))
+                        locations.append((os.path.join(root, filename), str(lineno + 1)))
                         strings[string] = locations
+    return strings
+
+
+def create_gettext_js(js_dir):
+    string_re = re.compile('_\\(\'(.*?)\'\\)')
+    strings = {}
+    for root, dnames, files in os.walk(js_dir):
+        for filename in files:
+            if os.path.splitext(filename)[1] != '.js':
+                continue
+            for lineno, line in enumerate(open(os.path.join(root, filename))):
+                for match in string_re.finditer(line):
+                    string = match.group(1)
+                    locations = strings.get(string, [])
+                    locations.append((os.path.basename(filename), lineno + 1))
+                    strings[string] = locations
 
     gettext_tpl = '''GetText={maps:{},\
     add:function(string,translation) {this.maps[string]=translation},\
@@ -52,3 +98,9 @@ def create_gettext_js(js_dir):
 if __name__ == '__main__':
     gettext_fname = create_gettext_js(WEBUI_JS_DIR)
     print("Created '%s'" % gettext_fname)
+    missed_markup = check_missing_markup(WEBUI_JS_DIR)
+    if missed_markup:
+        print("Possible missed text for translation markup:")
+        for text, filenames in missed_markup.iteritems():
+            for filename_lineno in filenames:
+                print("{0:<58}    {1}".format(':'.join(filename_lineno), text))