hwdb: fix parser to work with newer pyparsing

keszybz · keszybz · commit f73d6895872c · 2022-03-29T18:15:05.000+02:00
The handling of whitespace in pyparsing is a bother. There's some
global state, and per-element state, and it's hard to get a handle on
things. With python3-pyparsing-2.4.7-10.fc36.noarch the grammar would
not match. After handling of tabs was fixed to not accept duplicate tabs,
the grammar passes.

It seems that the entry for usb:v8087p8087*
was generated incorrectly because we treated the interface line
(with two TABs) as a device line (with one TAB).
diff --git a/hwdb.d/20-usb-vendor-model.hwdb b/hwdb.d/20-usb-vendor-model.hwdb
@@ -69815,9 +69815,6 @@ usb:v8087p8008*
 usb:v8087p800A*
  ID_MODEL_FROM_DATABASE=Hub
 
-usb:v8087p8087*
- ID_MODEL_FROM_DATABASE=07da  Centrino Advanced-N 6235
-
 usb:v80EE*
  ID_VENDOR_FROM_DATABASE=VirtualBox
 
diff --git a/hwdb.d/ids_parser.py b/hwdb.d/ids_parser.py
@@ -6,7 +6,7 @@
 from pyparsing import (Word, White, Literal, Regex,
                        LineEnd, SkipTo,
                        ZeroOrMore, OneOrMore, Combine, Optional, Suppress,
-                       Group,
+                       Group, ParserElement,
                        stringEnd, pythonStyleComment)
 
 EOL = LineEnd().suppress()
@@ -20,6 +20,8 @@
 EMPTYLINE = LineEnd()
 text_eol = lambda name: Regex(r'[^\n]+')(name) + EOL
 
+ParserElement.set_default_whitespace_chars(' \n')
+
 def klass_grammar():
     klass_line = Literal('C ').suppress() + NUM2('klass') + text_eol('text')
     subclass_line = TAB + NUM2('subclass') + text_eol('text')
@@ -35,8 +37,12 @@ def klass_grammar():
 def usb_ids_grammar():
     vendor_line = NUM4('vendor') + text_eol('text')
     device_line = TAB + NUM4('device') + text_eol('text')
+    interface_line = TAB + TAB + NUM4('interface') + NUM4('interface2') + text_eol('text')
+    device = (device_line +
+              ZeroOrMore(Group(interface_line)
+                         ^ COMMENTLINE.suppress()))
     vendor = (vendor_line('VENDOR') +
-              ZeroOrMore(Group(device_line)('VENDOR_DEV*') ^ COMMENTLINE.suppress()))
+              ZeroOrMore(Group(device)('VENDOR_DEV*') ^ COMMENTLINE.suppress()))
 
     klass = klass_grammar()
 
