[grilo/wip/hadess/fix-grl-keys-extraction] grl-inspect: Fix core keys extraction

[Bastien Nocera <hadess src gnome org>]

commit 1c21f1d75bca39a2c9a7567e25c21b0bc08311b9
Author: Bastien Nocera <hadess hadess net>
Date:   Tue Jul 16 14:42:43 2019 +0200

    grl-inspect: Fix core keys extraction
    
    This fixes incorrectly duplicated keys in grl-core-keys.h which affected
    the output of metadata in grl-inspect by removing the C comments prior
    to processing the file.
    
    Before:
    $ sort grl-core-keys.h | uniq --repeated
    "GRL_METADATA_KEY_MB_RELEASE_GROUP_ID",
    
    After:
    $ sort grl-core-keys.h | uniq --repeated
    $

 tools/grilo-inspect/generate_core_keys.py | 24 ++++++++++++++++++++----
 1 file changed, 20 insertions(+), 4 deletions(-)
---
diff --git a/tools/grilo-inspect/generate_core_keys.py b/tools/grilo-inspect/generate_core_keys.py
index 1c28473..ddd2f3a 100644
--- a/tools/grilo-inspect/generate_core_keys.py
+++ b/tools/grilo-inspect/generate_core_keys.py
@@ -11,20 +11,37 @@
 import re
 import sys
 
+# From https://stackoverflow.com/a/241506
+def comment_remover(text):
+    def replacer(match):
+        s = match.group(0)
+        if s.startswith('/'):
+            return " " # note: a space and not an empty string
+        else:
+            return s
+    pattern = re.compile(
+        r'//.*?$|/\*.*?\*/|\'(?:\\.|[^\\\'])*\'|"(?:\\.|[^\\"])*"',
+        re.DOTALL | re.MULTILINE
+    )
+    return re.sub(pattern, replacer, text)
+
 if len(sys.argv) != 3:
     print("Usage: " + sys.argv[0] + " <input> <output>")
     exit(1)
 
 finput = open(sys.argv[1], "r")
+input_data = finput.read()
+input_data = comment_remover(input_data).split('\n')
+finput.close()
 foutput = open(sys.argv[2], "w")
 
 foutput.write("gchar *grl_core_keys[] = {\n")
 
 output_keys = False
-for line in finput:
-    if re.search("BEGIN CORE KEYS", line):
+for line in input_data:
+    if re.search("GRL_METADATA_KEY_ALBUM", line):
         output_keys = True
-    if re.search("END CORE KEYS", line):
+    if re.search("G_BEGIN_DECLS", line):
         output_keys = False
     m = re.search("GRL_METADATA_KEY_[^ ]+", line)
     if output_keys and m:
@@ -32,5 +49,4 @@ for line in finput:
 
 foutput.write("};");
 
-finput.close()
 foutput.close()