[PATCH v1 01/27] BaseTools: Misc - refactor RegEx to minimize multiple compiling

[Jaben Carsey <jaben.carsey@intel.com>]

Cc: Liming Gao <liming.gao@intel.com>
Cc: Yonghong Zhu <yonghong.zhu@intel.com>
Contributed-under: TianoCore Contribution Agreement 1.1
Signed-off-by: Jaben Carsey <jaben.carsey@intel.com>
---
 BaseTools/Source/Python/Common/Misc.py | 16 +++++++++++-----
 1 file changed, 11 insertions(+), 5 deletions(-)

diff --git a/BaseTools/Source/Python/Common/Misc.py b/BaseTools/Source/Python/Common/Misc.py
index 4f2bfd63cfc3..bc7d0c2d9d00 100644
--- a/BaseTools/Source/Python/Common/Misc.py
+++ b/BaseTools/Source/Python/Common/Misc.py
@@ -84,6 +84,7 @@ def _parseForXcode(lines, efifilepath, varnames):
         if status == 1 and len(line) != 0:
             for varname in varnames:
                 if varname in line:
+                    # cannot pregenerate this RegEx since it uses varname from varnames.
                     m = re.match('^([\da-fA-FxX]+)([\s\S]*)([_]*%s)$' % varname, line)
                     if m is not None:
                         ret.append((varname, m.group(1)))
@@ -91,6 +92,8 @@ def _parseForXcode(lines, efifilepath, varnames):
 
 def _parseForGCC(lines, efifilepath, varnames):
     """ Parse map file generated by GCC linker """
+    valuePattern = re.compile('^([\w_\.]+) +([\da-fA-Fx]+) +([\da-fA-Fx]+)$')
+    pcdPattern = re.compile('^([\da-fA-Fx]+) +([\da-fA-Fx]+)')
     status = 0
     sections = []
     varoffset = []
@@ -109,7 +112,7 @@ def _parseForGCC(lines, efifilepath, varnames):
 
         # status handler
         if status == 3:
-            m = re.match('^([\w_\.]+) +([\da-fA-Fx]+) +([\da-fA-Fx]+)$', line)
+            m = valuePattern.match(line)
             if m is not None:
                 sections.append(m.groups(0))
             for varname in varnames:
@@ -122,7 +125,7 @@ def _parseForGCC(lines, efifilepath, varnames):
                     else:
                         Str = line[len(".data.%s" % varname):]
                     if Str:
-                        m = re.match('^([\da-fA-Fx]+) +([\da-fA-Fx]+)', Str.strip())
+                        m = pcdPattern.match(Str.strip())
                         if m is not None:
                             varoffset.append((varname, int(m.groups(0)[0], 16) , int(sections[-1][1], 16), sections[-1][0]))
 
@@ -152,16 +155,18 @@ def _parseGeneral(lines, efifilepath, varnames):
     varoffset = []
     secRe = re.compile('^([\da-fA-F]+):([\da-fA-F]+) +([\da-fA-F]+)[Hh]? +([.\w\$]+) +(\w+)', re.UNICODE)
     symRe = re.compile('^([\da-fA-F]+):([\da-fA-F]+) +([\.:\\\\\w\?@\$]+) +([\da-fA-F]+)', re.UNICODE)
+    startRe = re.compile("^Start[' ']+Length[' ']+Name[' ']+Class")
+    addressRe = re.compile("^Address[' ']+Publics by Value[' ']+Rva\+Base")
 
     for line in lines:
         line = line.strip()
-        if re.match("^Start[' ']+Length[' ']+Name[' ']+Class", line):
+        if startRe.match(line):
             status = 1
             continue
-        if re.match("^Address[' ']+Publics by Value[' ']+Rva\+Base", line):
+        if addressRe.match(line):
             status = 2
             continue
-        if re.match("^entry point at", line):
+        if line.startswith("entry point at"):
             status = 3
             continue        
         if status == 1 and len(line) != 0:
@@ -177,6 +182,7 @@ def _parseGeneral(lines, efifilepath, varnames):
                 sec_no     = int(sec_no,     16)
                 sym_offset = int(sym_offset, 16)
                 vir_addr   = int(vir_addr,   16)
+                # cannot pregenerate this RegEx since it uses varname from varnames.
                 m2 = re.match('^[_]*(%s)' % varname, sym_name)
                 if m2 is not None:
                     # fond a binary pcd entry in map file
-- 
2.16.2.windows.1