alternatives search algo

Author: taedmonds

.gitignore

@@ -1,4 +1,6 @@
 *.example.py
 *.pdf
 *.backup.py
+backups
+backups/*
 __pycache__

regex.py

@@ -2,11 +2,6 @@
 def is_start_set(char):
     return char == '[' or char == '('
 
-def match_star(start, end, txt):
-    # for i in range(len(txt) + 1):
-    return [True]
-
-
 # extract set from expression
 def extract_set(char, exp):
     end_pos = 0
@@ -20,60 +15,86 @@ def extract_set(char, exp):
 
 # match range set
 def match_range(exp, txt, pos = 0):
-    if(len(txt) == 0):
-        return [True, pos]
-    
+    if(len(txt) == 0 or len(txt) - 1 == pos):
+        if(len(txt) - 1 == pos):
+            return [True, pos - 1]
+        else:
+            return [True, pos]
+
     # if string contains lowercase letters
     if('a-z' in exp):
-        if(txt[0] >= 'a' and txt[0] <= 'z'):
-            return match_range(exp, txt[1:], pos + 1)
+        if(txt[pos] >= 'a' and txt[pos] <= 'z'):
+            return match_range(exp, txt, pos + 1)
 
     # if string contains uppercase letters
     if('A-Z' in exp):
-        if(txt[0] >= 'A' and txt[0] <= 'Z'):
-            return match_range(exp, txt[1:], pos + 1)
+        if(txt[pos] >= 'A' and txt[pos] <= 'Z'):
+            return match_range(exp, txt, pos + 1)
 
     # if string contains integers
     if('0-9' in exp):
-        if(txt[0] >= '0' and txt[0] <= '9'):
-            return match_range(exp, txt[1:], pos + 1)
+        if(txt[pos] >= '0' and txt[pos] <= '9'):
+            return match_range(exp, txt, pos + 1)
 
     return [False, pos]
 
 # match options set
-def match_set(exp, txt):
+def match_set(exp, txt, pos = 0, end = 0):
+    if(end == len(txt)):
+        return [True, end]
+
     arr = exp.replace('(', '').replace(')', '').split('|')
-    return [txt in arr]
+    char = txt[end]
+
+    
+    if any(char in s for s in arr):
+        [matched, end] =  match_set(exp, txt, pos, end + 1)
+        
+        if(matched):
+            for item in arr:
+                if(item == txt[pos:end]):
+                    [matched, txt_pos] = match_exp(item, txt[pos:end], 0, 0)
+                    
+                    if (matched):
+                        return [True, end]
+                    else:
+                        return [False, pos + txt_pos]
+    
+    return [False, pos]
 
 
 # find match of the expression in the text
 def match_exp(exp, txt, txt_pos = 0, exp_pos = 0):
     # if expression is empty - we have checked all
     if (len(exp) == 0):
-        return True
+        return [True, txt_pos]
 
     # if match set of characters
     if(is_start_set(exp[exp_pos])):
         [set_exp, exp_pos] = extract_set(exp[exp_pos], exp)
 
         if(exp[0] == '['):
-            [matched, txt_pos] = match_range(set_exp, txt)
+            [matched, txt_pos] = match_range(set_exp, txt, txt_pos)
+
             if(matched):
-                return True
+                return [True, txt_pos]
 
         elif(exp[0] == '('):
-            [matched] = match_set(set_exp, txt)
+            [matched, txt_pos] = match_set(set_exp, txt, txt_pos, txt_pos)
+
             if(matched):
-                return True
-    
+                return [True, txt_pos]
+
     # if character matches
     if(len(exp) > exp_pos and len(txt) > txt_pos):
         if (exp[exp_pos] == txt[txt_pos]):
-            if(match_exp(exp[(exp_pos + 1):], txt[(txt_pos + 1):])):
-                return True
+            [matched, txt_pos] = match_exp(exp[(exp_pos + 1):], txt, txt_pos + 1)
+            
+            if(matched):
+                return [True, txt_pos]
 
     # if nothing matches
-    return False
+    return [False, txt_pos]
 
 # if valid to start
 def is_valid(exp, txt):
@@ -88,7 +109,9 @@ def init_match(exp, txt):
     if (is_valid(exp, txt)):
         # naive algorithm
         while txt_pos < len(txt) - 1:
-            if (match_exp(exp, txt[txt_pos:])):
+            [matched, txt_pos] = match_exp(exp, txt, txt_pos)
+            
+            if (matched):
                 matched_count += 1
 
             elif(is_start_set(exp[0])):
@@ -98,9 +121,9 @@ def init_match(exp, txt):
 
     # if the matched count is greater than zero
     if (matched_count > 0):
-        return True
+        return [True, matched_count]
 
-    return False
+    return [False, 0]
 
 
 class RegEx:

test.py

@@ -3,9 +3,12 @@
 # run each test case
 def test(num, exp, txt):
     re = RegEx(exp)
+    result = re.match(txt)
+
     print("Pattern: ", exp)
     print("String: ", txt)
-    print(f"Test {num} result: ", re.match(txt), end='\n\n')
+    print(f"Test {num} result: ", result[0])
+    print(f"Match count: ", result[1], end='\n\n')
 
 
 if __name__ == '__main__':
@@ -32,15 +35,12 @@ def test(num, exp, txt):
             'string': '[email protected]',
         },
         {
-            'pattern': '[A-Z]',
-            'string': 'Hello',
+            'pattern': '[a-z0-9]@[a-z].(moc)',
+            'string': '[email protected]',
         },
-    ]
-    
-    tests_1 = [
         {
-            'pattern': '[a-z0-9]@[a-z].(com|net|org)',
-            'string': '[email protected]',
+            'pattern': '[A-Z]',
+            'string': 'Hello',
         },
     ]