consistent_company 0.0.4 → 0.0.5

data/VERSION

@@ -1 +1 @@
-0.1.0
+0.5.0

data/consistent_company.gemspec

@@ -5,11 +5,11 @@
 
 Gem::Specification.new do |s|
   s.name = %q{consistent_company}
-  s.version = "0.0.4"
+  s.version = "0.0.5"
 
   s.required_rubygems_version = Gem::Requirement.new(">= 0") if s.respond_to? :required_rubygems_version=
   s.authors = [%q{Doug Cleven}]
-  s.date = %q{2011-09-30}
+  s.date = %q{2011-10-06}
   s.description = %q{Ruby C Extension to normalize a company name. Useful when company names come from various sources.}
   s.email = %q{dcleven@marketron.com}
   s.extensions = [%q{ext/consistent_company/extconf.rb}]

data/ext/consistent_company/consistent_company.c

@@ -6,9 +6,8 @@
 
 char * TransformCompany(char * inString);
 static int IsCompanyWord(char * inWord);
-char *trimwhitespace(char *str);
-char *trimsuffix(char *str, const char *suffix);
-char *str_replace(char *orig, const char *rep, const char *with);
+char * trimwhitespace(char *str);
+char * str_replace(char *orig, const char *rep, const char *with);
 
 static VALUE rb_ConsistentCompany_Init(VALUE self)
 {
@@ -19,10 +18,12 @@ static VALUE rb_ConsistentCompany_Init(VALUE self)
 static VALUE rb_CompanyNamer(VALUE self)
 {
 	char * pSelf = RSTRING_PTR(self);
-	int selfLen = strlen(pSelf)+2;
-	int workLen = selfLen;
+	int selfLen = (int)strlen(pSelf)+2;
+	int workLen = (int)selfLen;
 	char * s = pSelf;
-	
+	if (*pSelf == '\0')
+		return self;
+			
 	// calc size of work strings
 	// while processing we turn & = AND, + = PLUS
 	// and we add space at front and back
@@ -31,7 +32,7 @@ static VALUE rb_CompanyNamer(VALUE self)
 		workLen +=3; // worst case we add 3 chars
 		s++;
 	}
-	workLen += 2;	// add space front and back
+	workLen += 90;	// add space front and back
 	//////////////
 	
 	// for company only
@@ -50,7 +51,7 @@ static VALUE rb_CompanyNamer(VALUE self)
 		inString[i] = toupper( inString[i] );
 	
 	inString = trimwhitespace(inString);
-	unsigned long len = strlen(inString);
+	int len = (int)strlen(inString);
 	for (i = 0; i < len; i++)
 	{
 		if (inString[i] == '(')
@@ -79,7 +80,7 @@ static VALUE rb_CompanyNamer(VALUE self)
 		{
 			// ..(xx)..
 			inString[left1++] = ' ';
-			strcpy(&inString[left1], &inString[right1+1]);		
+			memmove(&inString[left1], &inString[right1+1], strlen(inString+right1+1)+1);		
 		}
 		else
 			// ..(xx
@@ -91,21 +92,21 @@ static VALUE rb_CompanyNamer(VALUE self)
 		{
 			// ..(xx)..(xx)..
 			inString[left1] = ' ';
-			strncpy(inString + left1 + 1, inString + right1 + 1, left2-right1-1);
+			memmove(inString + left1 + 1, inString + right1 + 1, left2-right1-1);
 			inString[left1+1+left2-right1-1]  = ' ';
-			strcpy(inString+left1+1+left2-right1, inString + right2+1);
+			memmove(inString+left1+1+left2-right1, inString + right2+1, strlen(inString+right2+1)+1);
 		}
 		else if ((left1 < left2) && (left2 < right1) && (right1 < right2))
 		{
 			// ..(xx(xx)xx)..
 			inString[left1] = ' ';
-			strcpy(inString+left1+1, inString+right2+1);
+			memmove(inString+left1+1, inString+right2+1, strlen(inString+right2+1)+1);
 		}
 		else if ((left1 < right1) && (right1 < left2) && (right2 == -1))
 		{
 			// ..(xx)..(xx
 			inString[left1] = ' ';
-			strncpy(inString+left1+1, inString+right1+1, left2-right1-1);
+			memmove(inString+left1+1, inString+right1+1, left2-right1-1);
 			inString[left1+1+left2-right1] = '\0';
 		}
 		else if ((left1 < left2) && (left2 < right1) && (right2 == -1))
@@ -122,7 +123,7 @@ static VALUE rb_CompanyNamer(VALUE self)
 	char singleCharStr[2];
 	singleCharStr[1] = '\0';
 	returnString[0] = '\0';
-	for (i = 0; i < strlen(inString); i++)
+	for (i = 0; i < (int)strlen(inString); i++)
 	{
 		ch = inString[i];
 		asc = (int)ch;
@@ -161,19 +162,11 @@ static VALUE rb_CompanyNamer(VALUE self)
 			strcat(returnString, " ");
 		}
 	}
-	// if (strlen(workString) > workLen || strlen(returnString) > workLen)
-	// {
-	// 	char buff[200];
-	// 	sprintf(buff, "workLen %d %s workString %d returnString %d %s", workLen, pSelf, strlen(workString), strlen(returnString), returnString);
-	// 	return rb_str_new2(trimwhitespace(buff));
-	// }
-	char * p;
+	
 	str_replace(returnString, " AND ", " & ");
 	
-	int oldLen = strlen(returnString);
-//	returnString = trimsuffix(returnString, "s");	
 	returnString = trimwhitespace(returnString);
-	strcpy(returnString, TransformCompany(returnString));
+	returnString = TransformCompany(returnString);
 	VALUE return_value = rb_str_new2(trimwhitespace(returnString));
 	free(returnString);
 	free(workString);
@@ -190,16 +183,15 @@ FIRST FEDERAL SAVINGS becomes 1ST FEDERAL SAVINGS
 char * TransformCompany(char * resultString)
 {
 	// resultString should have been allocated with 2 extra char for our padding here
-	char * buf = malloc(strlen(resultString)+3);
+	char * buf = malloc(strlen(resultString)+30);
 	strcpy(buf, " ");
 	strcat(buf,resultString);
 	strcat(buf, " ");
 	strcpy(resultString, buf);
 	free(buf);
-	
+
 	char * spaceLoc;
 	char * s = resultString;
-
 	str_replace(s, " THE ", " ");
 	str_replace(s, " ONE ", " 1 ");
 	str_replace(s, " TWO ", " 2 ");
@@ -228,7 +220,6 @@ char * TransformCompany(char * resultString)
 	str_replace(s, " CENTRE ", " CTR ");
 	str_replace(s, " CENTER ", " CTR ");
 	str_replace(s, " CNTR ", " CTR ");
-	str_replace(s, " CTR ", " CTR ");
 	str_replace(s, " CENT ", " CTR ");
 	str_replace(s, " CENTR ", " CTR ");
 	str_replace(s, " AUTOMOTIVE ", " AUTO ");
@@ -251,11 +242,12 @@ char * TransformCompany(char * resultString)
 	str_replace(s, " INTERNATIONAL ", " INT ");
 	str_replace(s, " INTERNATION ", " INT ");
 	str_replace(s, " INTL ", " INT ");
-	str_replace(s, " MARKETING ", " MKTG ");
+	str_replace(s, " MARKETING ", " MKT ");
+	str_replace(s, " MKTG ", " MKT ");
 	str_replace(s, " MANAGEMENT ", " MGT ");
 	str_replace(s, " MGMT ", " MGT ");
 
-	s = trimwhitespace(s);
+	s = trimwhitespace(s);	
 	spaceLoc = strstr(s, " ");
 	//spaceLoc = resultString.IndexOf(" ");
 	if (spaceLoc && strlen(s) > 3) // More than one word and more than 3 chars
@@ -268,7 +260,7 @@ char * TransformCompany(char * resultString)
 			strncmp(s+3, " ", 1) != 0 &&
 			strstr(s, "PLUS") != s + 2)
 		{
-			strcpy(s, s+2);
+			memmove(s, s+2, strlen(s+2)+1);
 		}
 
 		spaceLoc = strrchr(s, ' ');
@@ -283,6 +275,8 @@ char * TransformCompany(char * resultString)
 				spaceLoc = strrchr(s, ' ');
 				if (spaceLoc)  // Look at the new last word
 				{
+					free(lastWord);
+					lastWord = malloc(strlen(spaceLoc)+1);
 					strcpy(lastWord, spaceLoc + 1);
 					if (IsCompanyWord(lastWord))
 					{
@@ -295,8 +289,7 @@ char * TransformCompany(char * resultString)
 		if (s[strlen(s)-1] == '&')
 			s[strlen(s)-1] = '\0';
 	}
-
-	str_replace(s, " ", "");
+	s = str_replace(s, " ", "");
 	return s;
 }
 
@@ -367,73 +360,41 @@ int IsCompanyWord(char * inWord)
 
 /*
 Trim whitespace from front and back of string
+return the same ptr as received, move the non-whitespace chars
+to the front and trim the end with \0
 */
-char *trimwhitespace(char *str)
+char * trimwhitespace(char *str)
 {
-  char *end;
+	char *end;
+	char *start = str;
+	// Trim leading space
+	while(isspace(*str)) str++;
 
-  // Trim leading space
-  while(isspace(*str)) str++;
-
-  if(*str == 0)  // All spaces?
-    return str;
-
-  // Trim trailing space
-  end = str + strlen(str) - 1;
-  while(end > str && isspace(*end)) end--;
-
-  // Write new null terminator
-  *(end+1) = 0;
-
-  return str;
-}
-
-char *trimsuffix(char *str, const char *suffix)
-{
-	char delims[] = " ";
-	char *result = NULL;
-	char *workString = malloc(strlen(str)+3);
-	char *workBuffer = malloc(strlen(str)+3);
-	strcpy(workString, str);
-	str[0] = '\0';
-	result = strtok(workString, delims);
-	while(result != NULL) 
+	if(*str == 0)  // All spaces?
 	{
-		strcpy(workBuffer, result);
-		int len = strlen(workBuffer);
-		if (len > 3)
-		{
-			if (workBuffer[len-1] == 'S')
-			{
-				char * p = strstr(workBuffer, "IES");
-				if (p && p[3] == '\0' && strcmp(workBuffer, "SERIES") != 0)
-				{
-					*p = 'Y';
-					*++p = '\0';
-				}
-				if (strcmp(workBuffer, "PLUS") != 0)
-					workBuffer[len-1] = '\0';
-			}	
-		}
-		strcat(str, workBuffer);
-	    result = strtok( NULL, delims );
-		if (result)
-			strcat(str, " ");
+		*start = '\0';
+	  	return start;
 	}
-	free(workString);
-	free(workBuffer);
-	return str;
+	// Trim trailing space
+	end = str + strlen(str) - 1;
+	while(end > str && isspace(*end)) end--;
+
+	// Write new null terminator
+	*(end+1) = 0;
+	memmove(start, str, strlen(str)+1);
+	
+	return start;
 }
 
 
 // !!!! This ONLY works where rep is longer than with
-char *str_replace(char *orig, const char *rep, const char *with)
+char * str_replace(char *orig, const char *rep, const char *with)
 {
 	char * s = orig;
 	while (s=strstr(s, rep))
 	{
-		strncpy(s, with, strlen(with));
-		strcpy(s+strlen(with), s+strlen(rep));
+		memmove(s, with, strlen(with));
+		memmove(s+strlen(with), s+strlen(rep), strlen(s+strlen(rep))+1);
 		s = s + strlen(with)-1;
 	}
 	return orig;

data/lib/consistent_company/version.rb

@@ -2,7 +2,7 @@ module ConsistentCompany
   module Version
      MAJOR = 0
      MINOR = 0
-     PATCH = 4
+     PATCH = 5
      BUILD = nil
 
      STRING = [MAJOR, MINOR, PATCH, BUILD].compact.join('.')

data/test/test_consistent_company.rb

@@ -9,6 +9,10 @@ class TestConsistentCompany < Test::Unit::TestCase
     str = ' my test '
     company = str.company_namer
     assert_equal(' my test ', str) 
+    # empty name
+    assert_equal("", "".company_namer)
+    assert_equal("", " ".company_namer)
+    assert_equal("", "___".company_namer)
     # remove leading and trailing space
     assert_equal('TEST', " test ".company_namer)
     # remove embedded space
@@ -21,8 +25,6 @@ class TestConsistentCompany < Test::Unit::TestCase
     assert_equal("AAA", "The AAA Company".company_namer)
     # remove punctuation
     assert_equal("TESTERS", %q{The, ?%^* tester's company!}.company_namer)
-    # empty name
-    assert_equal("", "".company_namer)
     # a very long name
     assert_equal("A"*1000+"NAMEISHERE", (" A"*1000 + 'NAME IS HERE ').company_namer)
     # parenthesis matching

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: consistent_company
 version: !ruby/object:Gem::Version
-  version: 0.0.4
+  version: 0.0.5
   prerelease: 
 platform: ruby
 authors:
@@ -9,11 +9,11 @@ authors:
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2011-09-30 00:00:00.000000000Z
+date: 2011-10-06 00:00:00.000000000Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: shoulda
-  requirement: &70187182156920 !ruby/object:Gem::Requirement
+  requirement: &70092755072840 !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ! '>='
@@ -21,10 +21,10 @@ dependencies:
         version: '0'
   type: :development
   prerelease: false
-  version_requirements: *70187182156920
+  version_requirements: *70092755072840
 - !ruby/object:Gem::Dependency
   name: bundler
-  requirement: &70187182156220 !ruby/object:Gem::Requirement
+  requirement: &70092755071920 !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ~>
@@ -32,10 +32,10 @@ dependencies:
         version: 1.0.18
   type: :development
   prerelease: false
-  version_requirements: *70187182156220
+  version_requirements: *70092755071920
 - !ruby/object:Gem::Dependency
   name: jeweler
-  requirement: &70187182155600 !ruby/object:Gem::Requirement
+  requirement: &70092755070940 !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ~>
@@ -43,10 +43,10 @@ dependencies:
         version: 1.6.4
   type: :development
   prerelease: false
-  version_requirements: *70187182155600
+  version_requirements: *70092755070940
 - !ruby/object:Gem::Dependency
   name: rcov
-  requirement: &70187182154960 !ruby/object:Gem::Requirement
+  requirement: &70092755070060 !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ! '>='
@@ -54,10 +54,10 @@ dependencies:
         version: '0'
   type: :development
   prerelease: false
-  version_requirements: *70187182154960
+  version_requirements: *70092755070060
 - !ruby/object:Gem::Dependency
   name: pry
-  requirement: &70187182154360 !ruby/object:Gem::Requirement
+  requirement: &70092755068760 !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ! '>='
@@ -65,10 +65,10 @@ dependencies:
         version: '0'
   type: :development
   prerelease: false
-  version_requirements: *70187182154360
+  version_requirements: *70092755068760
 - !ruby/object:Gem::Dependency
   name: rake-compiler
-  requirement: &70187182153680 !ruby/object:Gem::Requirement
+  requirement: &70092755067580 !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ~>
@@ -76,7 +76,7 @@ dependencies:
         version: 0.7.6
   type: :development
   prerelease: false
-  version_requirements: *70187182153680
+  version_requirements: *70092755067580
 description: Ruby C Extension to normalize a company name. Useful when company names
   come from various sources.
 email: dcleven@marketron.com
@@ -117,7 +117,7 @@ required_ruby_version: !ruby/object:Gem::Requirement
       version: '0'
       segments:
       - 0
-      hash: 3110059090780389810
+      hash: 3143384625833077520
 required_rubygems_version: !ruby/object:Gem::Requirement
   none: false
   requirements: