tardistance 0.0.0

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA1:
+  metadata.gz: ca244b08fa65deb122012d7b221e524b0e40c9cd
+  data.tar.gz: 3f263ccd9557f0b206892d10b30e52d8b78885e4
+SHA512:
+  metadata.gz: 7a293d72090747165a3ffaa3f953501ec0b489abea27b1a33e95da488c21a04a45e27fbd1ac24dc90ff479c9a5c475c20d0ed3738f207b636400fccab64c38ec
+  data.tar.gz: 24c2be5411aed95846ced230403f9f156a2e573b2dd165438c6fbe3aee4bc48a27644f426524f58156bb4ed71059fa66c7dbc34a508b4de36d4dd690c9d625e8

data/ext/tardistance/extconf.rb

@@ -0,0 +1,3 @@
+require 'mkmf'
+create_header
+create_makefile 'tardistance/tardistance'

data/ext/tardistance/tardistance.c

@@ -0,0 +1,103 @@
+#include <ruby.h>
+#include <extconf.h>
+
+char **getWordsArray(VALUE rarray);
+char *getString(void);
+double findDistance(char*,char*,int,int);
+int min(int,int,int);
+int findMin(int,int);
+
+VALUE distance(VALUE self,VALUE str,VALUE rarray,VALUE cutoff) {
+	int arrayLen =  RARRAY_LEN(rarray);
+	int stringLength = RSTRING_LEN(str);
+	long i =0;
+	long j=0;
+	long finalCount = 0;
+	char *searchWord;
+	char *data[1000];
+	int dataLen[1000];
+	VALUE finalResult[1000];
+	double  cutoffScore = -1.0;
+	if(!NIL_P(cutoff)){
+		cutoffScore = NUM2DBL(cutoff);
+	}
+	if(cutoffScore < 0.0){
+		cutoffScore = 0.5;
+	}
+	if(!NIL_P(rarray) && arrayLen > 0 && arrayLen <= 1000 && stringLength > 0 && stringLength <= 100){
+		while(i < arrayLen){
+			VALUE element = rb_ary_entry(rarray,i);
+			data[i] = StringValuePtr(element);
+			dataLen[i] = RSTRING_LEN(element);
+			i++;
+		}
+		searchWord = (char*)StringValuePtr(str);
+		while(j<i){
+			if(findDistance(data[j],searchWord,dataLen[j],stringLength) <= cutoffScore){
+				finalResult[finalCount] = rb_str_new_cstr(data[j]);
+				finalCount++;
+			}
+			j++;
+		}
+	}else{
+		return rb_str_new2("Error:null value passed");
+	}
+	return rb_ary_new4(finalCount,finalResult);
+}
+
+double findDistance(char* dataStr,char* searchWord,int dataLen,int searchWordLen){
+	int k = 0 ,l = 0;
+    int dp[1001][101];
+	if (dataLen <= 1000 && searchWordLen <= 100){
+		char *a =dataStr;
+		char *b =searchWord;
+	   	for (k=0; k<=dataLen; k++){
+	   		b =searchWord;
+	        for (l=0; l<=searchWordLen; l++){
+	            if (k==0){
+	                dp[k][l] = l;
+	            }
+	            else if (l==0){
+	                dp[k][l] = k;
+	            }
+	            else if ( *a == *b){
+	                dp[k][l] = dp[k-1][l-1];
+	            }
+
+	            else{
+	                dp[k][l] = 1 + min(dp[k][l-1],  // Insert
+	                                   dp[k-1][l],  // Remove
+	                                   dp[k-1][l-1]); // Replace
+	            }
+	            b++;
+	        }
+	        a++;
+	    }
+	}
+    return ((double)dp[k-1][l-1]/searchWordLen);
+}
+
+int min(int x,int y,int z){
+	return findMin(x,findMin(x,y));
+}
+int findMin(int r,int s){
+	if (r < s){
+		return r;
+	}
+	else{
+		return s;
+	}
+}
+
+void Init_tardistance()
+{
+  VALUE mod = rb_define_module("PercentSearch");
+  rb_define_global_function("distance",distance,3);
+}
+
+int main()
+{
+	/* code */
+	printf("Hello World\n");
+	return 0;
+}

data/lib/tardistance.rb

@@ -0,0 +1,12 @@
+
+class Tardistance
+	require_relative 'tardistance/tardistance'
+    include PercentSearch
+	def self.percent_change(search_string,search_array,percent_diff)
+		if search_array.kind_of?(Array) and search_string.is_a?(String) and percent_diff.is_a?(Numeric)
+			return distance(search_string,search_array,percent_diff)
+		else
+			raise "Invalid Parameters please pass percent_change(string,array,decimal)"
+		end
+	end
+end

metadata

@@ -0,0 +1,50 @@
+--- !ruby/object:Gem::Specification
+name: tardistance
+version: !ruby/object:Gem::Version
+  version: 0.0.0
+platform: ruby
+authors:
+- Tarash Agarwal
+autorequire: 
+bindir: bin
+cert_chain: []
+date: 2018-07-13 00:00:00.000000000 Z
+dependencies: []
+description: Filter strings on basis of percentage of changes to be made in the string
+  in terms of levenshtein distance by string length
+email: tarash.agarwal@gmail.com
+executables: []
+extensions:
+- ext/tardistance/extconf.rb
+extra_rdoc_files: []
+files:
+- ext/tardistance/extconf.rb
+- ext/tardistance/tardistance.c
+- lib/tardistance.rb
+homepage: https://github.com/tarashagarwal/tardistance.git
+licenses:
+- MIT
+metadata:
+  authors_blog: https://tarashagarwal.github.io/
+  levenshtein distance algorithm: https://en.wikipedia.org/wiki/Levenshtein_distance
+post_install_message: 
+rdoc_options: []
+require_paths:
+- lib
+required_ruby_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ">="
+    - !ruby/object:Gem::Version
+      version: '0'
+required_rubygems_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ">="
+    - !ruby/object:Gem::Version
+      version: '0'
+requirements: []
+rubyforge_project: 
+rubygems_version: 2.6.13
+signing_key: 
+specification_version: 4
+summary: A fast method to filter strings
+test_files: []