crc check for external files to compile; bugfix: os.parseCmdLine

2 files changed, 81 insertions, 19 deletions

diff --git a/lib/pure/os.nim b/lib/pure/os.nim
index f807c39f5..129774f6e 100755
--- a/lib/pure/os.nim
+++ b/lib/pure/os.nim
@@ -926,28 +926,90 @@ proc createDir*(dir: string) =
   rawCreateDir(dir)
 
 proc parseCmdLine*(c: string): seq[string] =
-  ## Splits a command line into several components; components are separated by
-  ## whitespace unless the whitespace occurs within ``"`` or ``'`` quotes. 
+  ## Splits a command line into several components;  
   ## This proc is only occassionally useful, better use the `parseopt` module.
+  ##
+  ## On Windows, it uses the following parsing rules
+  ## (see http://msdn.microsoft.com/en-us/library/17w5ykft.aspx):
+  ##
+  ## * Arguments are delimited by white space, which is either a space or a tab.
+  ## * The caret character (^) is not recognized as an escape character or
+  ##   delimiter. The character is handled completely by the command-line parser
+  ##   in the operating system before being passed to the argv array in the
+  ##   program.
+  ## * A string surrounded by double quotation marks ("string") is interpreted
+  ##   as a single argument, regardless of white space contained within. A
+  ##   quoted string can be embedded in an argument.
+  ## * A double quotation mark preceded by a backslash (\") is interpreted as a
+  ##   literal double quotation mark character (").
+  ## * Backslashes are interpreted literally, unless they immediately precede
+  ##   a double quotation mark.
+  ## * If an even number of backslashes is followed by a double quotation mark,
+  ##   one backslash is placed in the argv array for every pair of backslashes,
+  ##   and the double quotation mark is interpreted as a string delimiter.
+  ## * If an odd number of backslashes is followed by a double quotation mark,
+  ##   one backslash is placed in the argv array for every pair of backslashes,
+  ##   and the double quotation mark is "escaped" by the remaining backslash,
+  ##   causing a literal double quotation mark (") to be placed in argv.
+  ##
+  ## On Posix systems, it uses the following parsing rules:
+  ## components are separated by
+  ## whitespace unless the whitespace occurs within ``"`` or ``'`` quotes.
   result = @[]
   var i = 0
   var a = ""
   while true:
     setLen(a, 0)
-    while c[i] >= '\1' and c[i] <= ' ': inc(i) # skip whitespace
-    case c[i]
-    of '\'', '\"':
-      var delim = c[i]
-      inc(i) # skip ' or "
-      while c[i] != '\0' and c[i] != delim:
-        add a, c[i]
-        inc(i)
-      if c[i] != '\0': inc(i)
-    of '\0': break
+    while c[i] == ' ' or c[i] == '\t': inc(i)
+    when defined(windows):
+      # parse a single argument according to the above rules:
+      var inQuote = false
+      while true:
+        case c[i]        
+        of '\0': break
+        of '\\':
+          var j = i
+          while c[j] == '\\': inc(j)
+          if c[j] == '"': 
+            for k in 0..(j-i) div 2: a.add('\\')
+            if (j-i) mod 2 == 0: 
+              i = j
+            else: 
+              a.add('"')
+              i = j+1
+          else: 
+            a.add(c[i])
+            inc(i)
+        of '"':
+          inc(i)
+          if not inQuote: inQuote = true
+          elif c[i] == '"': 
+            a.add(c[i])
+            inc(i)
+          else:
+            inQuote = false
+            break
+        of ' ', '\t': 
+          if not inQuote: break
+          a.add(c[i])
+          inc(i)
+        else:
+          a.add(c[i])
+          inc(i)
     else:
-      while c[i] > ' ':
-        add(a, c[i])
-        inc(i)
+      case c[i]
+      of '\'', '\"':
+        var delim = c[i]
+        inc(i) # skip ' or "
+        while c[i] != '\0' and c[i] != delim:
+          add a, c[i]
+          inc(i)
+        if c[i] != '\0': inc(i)
+      of '\0': break
+      else:
+        while c[i] > ' ':
+          add(a, c[i])
+          inc(i)
     add(result, a)
 
 type
diff --git a/lib/system.nim b/lib/system.nim
index 66c5b4dfd..a83812ed0 100755
--- a/lib/system.nim
+++ b/lib/system.nim
@@ -233,9 +233,9 @@ type
                              ## that is too small to be represented as 
                              ## a normal number
   EFloatInexact* {.compilerproc.} = 
-    object of EFloatingPoint ## Inexact. Operation produces a result that cannot 
-                             ## be represented with infinite precision -- 
-                             ## for example, 2.0 / 3.0, log(1.1) 
+    object of EFloatingPoint ## Inexact. Operation produces a result
+                             ## that cannot be represented with infinite
+                             ## precision -- for example, 2.0 / 3.0, log(1.1) 
                              ## NOTE: Nimrod currently does not detect these!
 
   TResult* = enum Failure, Success
@@ -962,7 +962,7 @@ proc `$` *(x: Cstring): string {.magic: "CStrToStr", noSideEffect.}
 proc `$` *(x: string): string {.magic: "StrToStr", noSideEffect.}
   ## The stingify operator for a string argument. Returns `x`
   ## as it is. This operator is useful for generic code, so
-  ## that ``$expr`` also works if ``expr`` is already a string.
+  ## that ``$expr`` also works if ``expr`` already is a string.
 
 proc `$` *[T](x: ordinal[T]): string {.magic: "EnumToStr", noSideEffect.}
   ## The stingify operator for an enumeration argument. This works for