ENH: add method to attempt to check if a file is text or binary

2 files changed, 80 insertions, 1 deletions

diff --git a/Source/kwsys/SystemTools.cxx b/Source/kwsys/SystemTools.cxx
index a45ce40..a6d4e34 100644
--- a/Source/kwsys/SystemTools.cxx
+++ b/Source/kwsys/SystemTools.cxx
@@ -2748,6 +2748,65 @@ bool SystemTools::FileHasSignature(const char *filename,
   return res;
 }
 
+SystemTools::FileTypeEnum 
+SystemTools::DetectFileType(const char *filename,
+                            unsigned long length, 
+                            double percent_bin)
+{
+  if (!filename || percent_bin < 0)
+    {
+    return SystemTools::FileTypeUnknown;
+    }
+
+  FILE *fp;
+  fp = fopen(filename, "rb");
+  if (!fp)
+    {
+    return SystemTools::FileTypeUnknown;
+    }
+
+  // Allocate buffer and read bytes
+
+  unsigned char *buffer = new unsigned char [length];
+  size_t read_length = fread(buffer, 1, length, fp);
+  fclose(fp);
+  if (read_length == 0)
+    {
+    return SystemTools::FileTypeUnknown;
+    }
+
+  // Loop over contents and count
+
+  size_t text_count = 0;
+ 
+  const unsigned char *ptr = buffer;
+  const unsigned char *buffer_end = buffer + read_length;
+
+  while (ptr != buffer_end)
+    {
+    if ((*ptr >= 0x20 && *ptr <= 0x7F) || 
+        *ptr == '\n' ||
+        *ptr == '\r' ||
+        *ptr == '\t')
+      {
+      text_count++;
+      }
+    ptr++;
+    }
+
+  delete [] buffer;
+
+  double current_percent_bin =  
+    ((double)(read_length - text_count) / (double)read_length);
+
+  if (current_percent_bin >= percent_bin)
+    {
+    return SystemTools::FileTypeBinary;
+    }
+
+  return SystemTools::FileTypeText;
+}
+
 bool SystemTools::LocateFileInDir(const char *filename, 
                                   const char *dir, 
                                   kwsys_stl::string& filename_found,
diff --git a/Source/kwsys/SystemTools.hxx.in b/Source/kwsys/SystemTools.hxx.in
index 8654a67..31beafc 100644
--- a/Source/kwsys/SystemTools.hxx.in
+++ b/Source/kwsys/SystemTools.hxx.in
@@ -507,12 +507,32 @@ public:
   static bool FileIsSymlink(const char* name);
   
   /**
-   * return true if the file has a given signature (first set of bytes)
+   * Return true if the file has a given signature (first set of bytes)
    */
   static bool FileHasSignature(
     const char* filename, const char *signature, long offset = 0);
 
   /**
+   * Attempt to detect and return the type of a file.
+   * Up to 'length' bytes are read from the file, if more than 'percent_bin' %
+   * of the bytes are non-textual elements, the file is considered binary,
+   * otherwise textual. Textual elements are bytes in the ASCII [0x20, 0x7E]
+   * range, but also \n, \r, \t.
+   * The algorithm is simplistic, and should probably check for usual file
+   * extensions, 'magic' signature, unicode, etc.
+   */
+  enum FileTypeEnum 
+  { 
+    FileTypeUnknown,
+    FileTypeBinary,
+    FileTypeText
+  };
+  static SystemTools::FileTypeEnum DetectFileType(
+    const char* filename, 
+    unsigned long length = 256, 
+    double percent_bin = 0.05);
+
+  /**
    * Try to locate the file 'filename' in the directory 'dir'.
    * If 'filename' is a fully qualified filename, the basename of the file is
    * used to check for its existence in 'dir'.