added unistring type, working on parser

parse-input.cc

@@ -1,21 +1,26 @@
 
 #include <iostream>
+#include <string>
 #include <stdio.h>
 #include <ctype.h>  /* isspace() */
 #include "parse-input.h"
 using namespace std;
 
 #define SET_ERROR(err, args...) \
-    sprintf(errstr, err " at line %d, column %d", ##args, lineno, colno)
+    do { \
+        error = true; \
+        sprintf(errstr, err " at line %d, column %d", ##args, lineno, colno); \
+    } while(0)
 
 void parse_input(refptr< vector<unichar_t> > ucs)
 {
-    enum State { INITIAL, LB, SECTION_NAME, RB };
+    enum State { INITIAL, SECTION_NAME, RULES };
     State state = INITIAL;
     int lineno = 1;
     int colno = 1;
     bool error = false;
     char errstr[200];
+    unistring build_str;
 
     for (int i = 0, sz = ucs->size(); i < sz; i++)
     {
@@ -34,18 +39,36 @@ void parse_input(refptr< vector<unichar_t> > ucs)
             case INITIAL:
                 if (c == '[')
                 {
-                    state = LB;
+                    state = SECTION_NAME;
+                    build_str = "";
                 }
                 else if (isspace(c))
                 {
                 }
                 else
                 {
-                    error = true;
                     SET_ERROR("Unexpected character 0x%x (%c) in input file",
                             c, c);
                 }
                 break;
+            case SECTION_NAME:
+                switch (c)
+                {
+                    case ']':
+                        if (build_str == "rules")
+                        {
+                            state = RULES;
+                        }
+                        else
+                        {
+                            SET_ERROR("Unknown section name");
+                        }
+                        break;
+                    case '\n':
+                        SET_ERROR("Unterminated section header");
+                        break;
+                }
+                break;
         }
     }
 }

unicode.cc

@@ -0,0 +1,27 @@
+
+#include "unicode.h"
+#include <string.h>
+
+unistring & unistring::operator=(const char * ascii_str)
+{
+    chars.clear();
+    const char * as_ptr = ascii_str;
+    while (*as_ptr != '\0')
+    {
+        chars.push_back(*as_ptr);
+    }
+    return *this;
+}
+
+bool unistring::operator==(const char * ascii_str)
+{
+    int len = chars.size();
+    if (len != strlen(ascii_str))
+        return false;
+    for (int i = 0; i < len; i++)
+    {
+        if (chars[i] != ascii_str[i])
+            return false;
+    }
+    return true;
+}

unicode.h

@@ -2,7 +2,18 @@
 #ifndef UNICODE_H
 
 #include <stdint.h>
+#include <vector>
 
 typedef uint32_t unichar_t;
 
+class unistring
+{
+    public:
+        unistring & operator=(const char * ascii_str);
+        bool operator==(const char * ascii_str);
+
+    protected:
+        std::vector<unichar_t> chars;
+};
+
 #endif