csv_sniffer 0.1.1 → 0.1.2

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: ad85431534479a065a967c635b40262075688649
-  data.tar.gz: 1bf4f25c6628a1a83c06f36319d9178517d2f6c5
+  metadata.gz: 94eaa256ae4c389193159b7e22d4620a7fcd26a0
+  data.tar.gz: fb03dbd72b05013f2615f80053c577148959f83a
 SHA512:
-  metadata.gz: 75ab53bcd1b9db8a182ff93b09dbdbf59ac7a934fef724905248ead35b4fe3f2e0d07c88314a001d7145fa0ca29f3f65c22bcde5d88447e6fd7f34164711e892
-  data.tar.gz: ed4b9829deac6773b429d5217e5778df3581e8048b46e19170de1ad91b8c41b3bc5677d2f7548213c0c907dac90169e5fc9b22d6e4f754a2d93950517ab49092
+  metadata.gz: 7ce26eb29a3e246b597932fe3c66fca84fa5763a261a6c3e87e6af4565ced8b8178a439fe8b006b9435620caa72f992bd122423977097f9efea396569abffaa6
+  data.tar.gz: 63d1385bd21fc1362f6c4081c85857f22e1b397b33df92665c34f0c7c229f57b31e58d0dd4c4a1e93bdffe85c3ebe0b5dee3144620e185d4da88b759306d27b5

data/.gitignore

@@ -0,0 +1,2 @@
+*.gem
+

data/LICENSE

@@ -1,21 +1,21 @@
-The MIT License (MIT)
-
-Copyright (c) 2015 Tim Ojo
-
-Permission is hereby granted, free of charge, to any person obtaining a copy
-of this software and associated documentation files (the "Software"), to deal
-in the Software without restriction, including without limitation the rights
-to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
-copies of the Software, and to permit persons to whom the Software is
-furnished to do so, subject to the following conditions:
-
-The above copyright notice and this permission notice shall be included in
-all copies or substantial portions of the Software.
-
-THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
-IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
-FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
-AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
-LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
-OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
-THE SOFTWARE.
+The MIT License (MIT)
+
+Copyright (c) 2015 Tim Ojo
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in
+all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+THE SOFTWARE.

data/README.md

@@ -1,67 +1,67 @@
-# CSV Sniffer
-
-CSV Sniffer is a set of functions that allow a user heuristically detect the delimiter character in use, whether the values in the CSV file are quote enclosed, whether the file contains a header, and more. The library is intended to detect information to be used as configuration inputs for CSV parsers. For delimiter detection the following delimiters are currently supported `[",", "\t", "|", ";"]`
-
-To ensure high performance and a low memory footprint, the library uses as little information as needed to make accurate decisions. Contributors are welcome to
-improve the algorithms in use.
-
-
-## Installation
-
-```
-$ gem install csv_sniffer
-```
-
-## Usage
-
-Given a `some_file.csv` file:
-
-```csv
-Name;Phone
-John Doe ;555-481-2345
-Jane C. Doe;555-123-4567
-```
-
-Detection usage is as follows:
-
-```rb
-require "csv_sniffer"
-
-delim = CsvSniffer.detect_delimiter("/path/to/some_file.csv") #=> ";"
-is_quote_enclosed = CsvSniffer.is_quote_enclosed?("/path/to/some_file.csv") #=> false
-has_header = CsvSniffer.has_header?("/path/to/some_file.csv") #=> true
-```
-
-See [`test_csv_sniffer.rb`](test/test_csv_sniffer.rb) for more examples.
-
-
-## Tests
-
-```
-$ rake test
-```
-
-
-## License
-
-The MIT License (MIT)
-
-Copyright © 2015 Tim Ojo
-
-Permission is hereby granted, free of charge, to any person obtaining a copy
-of this software and associated documentation files (the "Software"), to deal
-in the Software without restriction, including without limitation the rights
-to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
-copies of the Software, and to permit persons to whom the Software is
-furnished to do so, subject to the following conditions:
-
-The above copyright notice and this permission notice shall be included in
-all copies or substantial portions of the Software.
-
-THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
-IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
-FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
-AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
-LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
-OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
-THE SOFTWARE.
+# CSV Sniffer
+
+CSV Sniffer is a set of functions that allow a user heuristically detect the delimiter character in use, whether the values in the CSV file are quote enclosed, whether the file contains a header, and more. The library is intended to detect information to be used as configuration inputs for CSV parsers. For delimiter detection the following delimiters are currently supported `[",", "\t", "|", ";"]`
+
+To ensure high performance and a low memory footprint, the library uses as little information as needed to make accurate decisions. Contributors are welcome to
+improve the algorithms in use.
+
+
+## Installation
+
+```
+$ gem install csv_sniffer
+```
+
+## Usage
+
+Given a `some_file.csv` file:
+
+```csv
+Name;Phone
+John Doe ;555-481-2345
+Jane C. Doe;555-123-4567
+```
+
+Detection usage is as follows:
+
+```rb
+require "csv_sniffer"
+
+delim = CsvSniffer.detect_delimiter("/path/to/some_file.csv") #=> ";"
+is_quote_enclosed = CsvSniffer.is_quote_enclosed?("/path/to/some_file.csv") #=> false
+has_header = CsvSniffer.has_header?("/path/to/some_file.csv") #=> true
+```
+
+See [`test_csv_sniffer.rb`](test/test_csv_sniffer.rb) for more examples.
+
+
+## Tests
+
+```
+$ rake test
+```
+
+
+## License
+
+The MIT License (MIT)
+
+Copyright © 2015 Tim Ojo
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in
+all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+THE SOFTWARE.

data/Rakefile

@@ -1,8 +1,8 @@
-require 'rake/testtask'
-
-Rake::TestTask.new do |t|
-  t.libs << 'test'
-end
-
-desc "Run tests"
-task :default => :test
+require 'rake/testtask'
+
+Rake::TestTask.new do |t|
+  t.libs << 'test'
+end
+
+desc "Run tests"
+task :default => :test

data/csv_sniffer.gemspec

@@ -1,15 +1,15 @@
-Gem::Specification.new do |s|
-  s.name        = 'csv_sniffer'
-  s.version     = '0.1.1'
-  s.date        = '2015-10-16'
-  s.summary     = "CSV library for heuristic detection of CSV properties"
-  s.description = "CSV Sniffer is a set of functions that allow a user detect the delimiter character in use, whether the values in the CSV file are quote enclosed, whether the file contains a header, and more. The library is intended to detect information to be used as configuration inputs for CSV parsers."
-  s.authors     = ["Tim Ojo"]
-  s.email       = 'ojo.tim@gmail.com'
-  s.homepage    = 'https://github.com/tim-ojo/csv_sniffer'
-  s.license     = 'MIT'
-
-  s.files       = `git ls-files`.split($/)
-  s.test_files  = s.files.grep(/^test/)
-  s.add_development_dependency "test-unit"
-end
+Gem::Specification.new do |s|
+  s.name        = 'csv_sniffer'
+  s.version     = '0.1.2'
+  s.date        = '2015-12-28'
+  s.summary     = "CSV library for heuristic detection of CSV properties"
+  s.description = "CSV Sniffer is a set of functions that allow a user detect the delimiter character in use, whether the values in the CSV file are quote enclosed, whether the file contains a header, and more. The library is intended to detect information to be used as configuration inputs for CSV parsers."
+  s.authors     = ["Tim Ojo"]
+  s.email       = 'ojo.tim@gmail.com'
+  s.homepage    = 'https://github.com/tim-ojo/csv_sniffer'
+  s.license     = 'MIT'
+
+  s.files       = `git ls-files`.split($/)
+  s.test_files  = s.files.grep(/^test/)
+  s.add_development_dependency 'test-unit', '~> 0'
+end

data/lib/csv_sniffer.rb

@@ -1,233 +1,245 @@
-# This class contains functions to heuristically decipher certain information from a CSV file
-class CsvSniffer
-
-    # Reads the first line of the csv and returns true if the line starts and ends with " or '
-    #
-    # Example:
-    #   CsvSniffer.is_quote_enclosed?("path/to/file")
-    #   =>  true
-    #
-    # Arguments:
-    #   filepath: (String)
-
-    def self.is_quote_enclosed?(filepath)
-      line = File.open(filepath, &:readline)
-      line.chomp!.strip!
-      return line.start_with?('"') && line.end_with?('"') || line.start_with?("'") && line.end_with?("'")
-    end
-
-
-    # Gets the quote character in use in the file if one exists. Returns "'", """ or nil
-    #
-    # Example:
-    #   CsvSniffer.get_quote_char("path/to/file")
-    #   =>  "
-    #
-    # Arguments:
-    #   filepath: (String)
-
-    def self.get_quote_char(filepath)
-      if is_quote_enclosed?(filepath)
-        line = File.open(filepath, &:readline)
-        line.chomp!.strip!
-        return line[0]
-      else
-        return nil
-      end
-    end
-
-
-    # Heuristically detects the delimiter used in the CSV file and returns it
-    #
-    # Example:
-    #   CsvSniffer.detect_delimiter("path/to/file")
-    #   =>  "|"
-    #
-    # Arguments:
-    #   filepath: (String)
-
-    def self.detect_delimiter (filepath)
-      # If the csv is quote enclosed then just get the delimiter after the first cell. Otherwise...
-      # Get the first line and count how many of the possible delimiters are present. If there is >1 of one of the
-      # delimiters and 0 of the others then, then we pick the max. If there are more than 0 of any of the others then
-      # we repeat the counting procedure for the next 50 lines until the condition is satisfied.
-      # If the condition is never satisfied then we simply pick the delimiter that occurs the most frequently, defaulting
-      # to the comma. Unless that delimeter's count is equal to the tab or pipe delimiter's count. In that case we return \t or |
-
-      if is_quote_enclosed?(filepath)
-        line = File.open(filepath, &:readline)
-        line.chomp!.strip!
-        m = /["'].+?["']([,|;\t])/.match(line)
-        if (m)
-          return m[1]
-        end
-      end
-
-      lineCount = 0
-      File.foreach(filepath) do |line|
-        detectedDelim = max_delim_when_others_are_zero(line)
-        if detectedDelim != '0' #=> '0' is a sentinel value that indicates no delim found
-          return detectedDelim
-        end
-
-        lineCount += 1;
-        break if lineCount == 50
-      end
-
-      # If I got here I'm going to pick the default by counting the delimiters on the first line and returning the max
-      line = File.open(filepath, &:readline)
-      freqOfPossibleDelims = get_freq_of_possible_delims(line)
-
-      maxFreq = 0
-      maxFreqIndex = 0
-      freqOfPossibleDelims.each_with_index do |delimFreq, i|
-        if (delimFreq > maxFreq)
-          maxFreq = delimFreq
-          maxFreqIndex = i
-        end
-      end
-
-      # Favor "\t" and "|" over ","
-      if (maxFreq == freqOfPossibleDelims[1])
-        return '\t'
-      elsif (maxFreq == freqOfPossibleDelims[3])
-        return "|"
-      else
-        return [",", '\t', ";", "|"][maxFreqIndex]
-      end
-    end
-
-    # Heuristically detects whether or not the csv file uses the first line as a header
-    #
-    # Example:
-    #   CsvSniffer.has_header?("path/to/file")
-    #   =>  false
-    #
-    # Arguments:
-    #   filepath: (String)
-
-    def self.has_header?(filepath)
-      # Creates a dictionary of types of data in each column. If any
-      # column is of a single type (say, integers), *except* for the first
-      # row, then the first row is presumed to be labels. If the type
-      # can't be determined, it is assumed to be a string in which case
-      # the length of the string is the determining factor: if all of the
-      # rows except for the first are the same length, it's a header.
-      # Finally, a 'vote' is taken at the end for each column, adding or
-      # subtracting from the likelihood of the first row being a header.
-      delim = detect_delimiter(filepath)
-      if (delim == "\\t")
-        delim = "\t"
-      end
-
-      headerRow = nil
-      lineCount = 0
-      columnTypes = Hash.new
-      File.foreach(filepath) do |line|
-        if (!headerRow) # assume the first row is a header
-          headerRow = line.split(delim)
-
-          headerRow.each_index do |colIndex|
-            columnTypes[colIndex] = nil
-          end
-          next
-        end
-
-        lineCount += 1
-        break if lineCount == 50
-
-        row = line.split(delim)
-        columnTypes.each_key do |colIndex|
-          thisColType = nil
-          if (row[colIndex].strip.to_i.to_s == row[colIndex])
-            thisColType = Integer
-          elsif (row[colIndex].strip.to_f.to_s == row[colIndex])
-            thisColType = Float
-          else
-            # fallback to the length of the string
-            thisColType = row[colIndex].strip.length
-          end
-
-          if (thisColType != columnTypes[colIndex])
-            if (columnTypes[colIndex] == nil)
-              # add new column type
-              columnTypes[colIndex] = thisColType
-            else
-              # type is inconsistent, remove from consideration
-              columnTypes[colIndex] = nil
-            end
-          end
-
-        end # end iterate through each row column to determine columnType
-      end # end iterate through each row
-
-      # finally, compare results against first row and "vote" on whether its a header
-      hasHeader = 0
-      columnTypes.each do |colIndex, colVal|
-        if colVal.class == NilClass
-          # ignore
-        elsif (colVal.class != Class) # it's a length
-          if (headerRow[colIndex].strip.length != colVal)
-            hasHeader += 1
-          else
-            hasHeader -= 1
-          end
-        else
-          # determine the type of the header and compare it to the type in the Hash
-          # if the type is the same then vote down otherwise vote up
-          if headerRow[colIndex].strip.to_i.to_s == headerRow[colIndex]
-            if colVal == Integer
-              hasHeader -= 1
-            else
-              hasHeader += 1
-            end
-          elsif headerRow[colIndex].strip.to_f.to_s == headerRow[colIndex]
-            if colVal == Float
-              hasHeader -= 1
-            else
-              hasHeader += 1
-            end
-          end
-        end # end type comparison voting branch
-      end # end voting loop
-
-      return hasHeader > 0
-    end
-
-    def self.max_delim_when_others_are_zero (line)
-      freqOfPossibleDelims = get_freq_of_possible_delims(line)
-
-      maxFreq = 0
-      maxFreqIndex = 0
-      zeroCount = 0
-      freqOfPossibleDelims.each_with_index do |delimFreq, i|
-        if (delimFreq > maxFreq)
-          maxFreq = delimFreq
-          maxFreqIndex = i
-        end
-        zeroCount += 1 if delimFreq == 0
-      end
-
-      if zeroCount >= 3
-        return [',', '\t', ';', '|'][maxFreqIndex]
-      else
-        return '0' #=> '0' is a sentinel value that indicates no delim found
-      end
-    end
-
-
-    def self.get_freq_of_possible_delims (line)
-      freqOfPossibleDelims = Array.new(4) #=> [0 = ','] [1 = '\t'] [2 = ';'] [3 = '|']
-      freqOfPossibleDelims[0] = line.count ","
-      freqOfPossibleDelims[1] = line.count "\t"
-      freqOfPossibleDelims[2] = line.count ";"
-      freqOfPossibleDelims[3] = line.count "|"
-
-      return freqOfPossibleDelims
-    end
-
-
-    private_class_method :max_delim_when_others_are_zero
-    private_class_method :get_freq_of_possible_delims
-
-end
+# This class contains functions to heuristically decipher certain information from a CSV file
+class CsvSniffer
+
+    # Reads the first line of the csv and returns true if the line starts and ends with " or '
+    #
+    # Example:
+    #   CsvSniffer.is_quote_enclosed?("path/to/file")
+    #   =>  true
+    #
+    # Arguments:
+    #   filepath: (String)
+
+    def self.is_quote_enclosed?(filepath)
+      begin
+        line = File.open(filepath, &:readline)
+        line.chomp!.strip!
+        return line.start_with?('"') && line.end_with?('"') || line.start_with?("'") && line.end_with?("'")
+      rescue EOFError
+        false
+      end
+    end
+
+
+    # Gets the quote character in use in the file if one exists. Returns "'", """ or nil
+    #
+    # Example:
+    #   CsvSniffer.get_quote_char("path/to/file")
+    #   =>  "
+    #
+    # Arguments:
+    #   filepath: (String)
+
+    def self.get_quote_char(filepath)
+      begin
+        if is_quote_enclosed?(filepath)
+          line = File.open(filepath, &:readline)
+          line.chomp!.strip!
+          return line[0]
+        else
+          return nil
+        end
+      rescue EOFError
+        nil
+      end
+    end
+
+
+    # Heuristically detects the delimiter used in the CSV file and returns it
+    #
+    # Example:
+    #   CsvSniffer.detect_delimiter("path/to/file")
+    #   =>  "|"
+    #
+    # Arguments:
+    #   filepath: (String)
+
+    def self.detect_delimiter (filepath)
+      # If the csv is quote enclosed then just get the delimiter after the first cell. Otherwise...
+      # Get the first line and count how many of the possible delimiters are present. If there is >1 of one of the
+      # delimiters and 0 of the others then, then we pick the max. If there are more than 0 of any of the others then
+      # we repeat the counting procedure for the next 50 lines until the condition is satisfied.
+      # If the condition is never satisfied then we simply pick the delimiter that occurs the most frequently, defaulting
+      # to the comma. Unless that delimeter's count is equal to the tab or pipe delimiter's count. In that case we return \t or |
+
+      if is_quote_enclosed?(filepath)
+        line = File.open(filepath, &:readline)
+        line.chomp!.strip!
+        m = /["'].+?["']([,|;\t])/.match(line)
+        if (m)
+          return m[1]
+        end
+      end
+
+      lineCount = 0
+      File.foreach(filepath) do |line|
+        detectedDelim = max_delim_when_others_are_zero(line)
+        if detectedDelim != '0' #=> '0' is a sentinel value that indicates no delim found
+          return detectedDelim
+        end
+
+        lineCount += 1;
+        break if lineCount == 50
+      end
+
+      # If I got here I'm going to pick the default by counting the delimiters on the first line and returning the max
+      begin
+        line = File.open(filepath, &:readline)
+        freqOfPossibleDelims = get_freq_of_possible_delims(line)
+      rescue EOFError
+        freqOfPossibleDelims = [0,-1,-1,-1]
+      end
+
+      maxFreq = 0
+      maxFreqIndex = 0
+      freqOfPossibleDelims.each_with_index do |delimFreq, i|
+        if (delimFreq > maxFreq)
+          maxFreq = delimFreq
+          maxFreqIndex = i
+        end
+      end
+
+      # Favor "\t" and "|" over ","
+      if (maxFreq == freqOfPossibleDelims[1])
+        return '\t'
+      elsif (maxFreq == freqOfPossibleDelims[3])
+        return "|"
+      else
+        return [",", '\t', ";", "|"][maxFreqIndex]
+      end
+    end
+
+    # Heuristically detects whether or not the csv file uses the first line as a header
+    #
+    # Example:
+    #   CsvSniffer.has_header?("path/to/file")
+    #   =>  false
+    #
+    # Arguments:
+    #   filepath: (String)
+
+    def self.has_header?(filepath)
+      # Creates a dictionary of types of data in each column. If any
+      # column is of a single type (say, integers), *except* for the first
+      # row, then the first row is presumed to be labels. If the type
+      # can't be determined, it is assumed to be a string in which case
+      # the length of the string is the determining factor: if all of the
+      # rows except for the first are the same length, it's a header.
+      # Finally, a 'vote' is taken at the end for each column, adding or
+      # subtracting from the likelihood of the first row being a header.
+      delim = detect_delimiter(filepath)
+      if (delim == "\\t")
+        delim = "\t"
+      end
+
+      headerRow = nil
+      lineCount = 0
+      columnTypes = Hash.new
+      File.foreach(filepath) do |line|
+        if (!headerRow) # assume the first row is a header
+          headerRow = line.split(delim)
+
+          headerRow.each_index do |colIndex|
+            columnTypes[colIndex] = nil
+          end
+          next
+        end
+
+        lineCount += 1
+        break if lineCount == 50
+
+        row = line.split(delim)
+        columnTypes.each_key do |colIndex|
+          thisColType = nil
+          if (row[colIndex].strip.to_i.to_s == row[colIndex])
+            thisColType = Integer
+          elsif (row[colIndex].strip.to_f.to_s == row[colIndex])
+            thisColType = Float
+          else
+            # fallback to the length of the string
+            thisColType = row[colIndex].strip.length
+          end
+
+          if (thisColType != columnTypes[colIndex])
+            if (columnTypes[colIndex] == nil)
+              # add new column type
+              columnTypes[colIndex] = thisColType
+            else
+              # type is inconsistent, remove from consideration
+              columnTypes[colIndex] = nil
+            end
+          end
+
+        end # end iterate through each row column to determine columnType
+      end # end iterate through each row
+
+      # finally, compare results against first row and "vote" on whether its a header
+      hasHeader = 0
+      columnTypes.each do |colIndex, colVal|
+        if colVal.class == NilClass
+          # ignore
+        elsif (colVal.class != Class) # it's a length
+          if (headerRow[colIndex].strip.length != colVal)
+            hasHeader += 1
+          else
+            hasHeader -= 1
+          end
+        else
+          # determine the type of the header and compare it to the type in the Hash
+          # if the type is the same then vote down otherwise vote up
+          if headerRow[colIndex].strip.to_i.to_s == headerRow[colIndex]
+            if colVal == Integer
+              hasHeader -= 1
+            else
+              hasHeader += 1
+            end
+          elsif headerRow[colIndex].strip.to_f.to_s == headerRow[colIndex]
+            if colVal == Float
+              hasHeader -= 1
+            else
+              hasHeader += 1
+            end
+          end
+        end # end type comparison voting branch
+      end # end voting loop
+
+      return hasHeader > 0
+    end
+
+    def self.max_delim_when_others_are_zero (line)
+      freqOfPossibleDelims = get_freq_of_possible_delims(line)
+
+      maxFreq = 0
+      maxFreqIndex = 0
+      zeroCount = 0
+      freqOfPossibleDelims.each_with_index do |delimFreq, i|
+        if (delimFreq > maxFreq)
+          maxFreq = delimFreq
+          maxFreqIndex = i
+        end
+        zeroCount += 1 if delimFreq == 0
+      end
+
+      if zeroCount >= 3
+        return [',', '\t', ';', '|'][maxFreqIndex]
+      else
+        return '0' #=> '0' is a sentinel value that indicates no delim found
+      end
+    end
+
+
+    def self.get_freq_of_possible_delims (line)
+      freqOfPossibleDelims = Array.new(4) #=> [0 = ','] [1 = '\t'] [2 = ';'] [3 = '|']
+      freqOfPossibleDelims[0] = line.count ","
+      freqOfPossibleDelims[1] = line.count "\t"
+      freqOfPossibleDelims[2] = line.count ";"
+      freqOfPossibleDelims[3] = line.count "|"
+
+      return freqOfPossibleDelims
+    end
+
+
+    private_class_method :max_delim_when_others_are_zero
+    private_class_method :get_freq_of_possible_delims
+
+end

data/test/test_csv_sniffer.rb

@@ -1,78 +1,86 @@
-require 'minitest/autorun'
-require 'tempfile'
-require 'csv_sniffer'
-
-class CsvSnifferTest < Minitest::Test
-
-  @@file1 = Tempfile.new('file1')
-  @@file1.puts "Name,Number"
-  @@file1.puts "John Doe,555-123-4567"
-  @@file1.puts "Jane C. Doe,555-000-1234"
-  @@file1.rewind
-
-  @@file2 = Tempfile.new('file2')
-  @@file2.puts "'Name' |'Number'\t"
-  @@file2.puts "'John Doe'|'555-123-4567'"
-  @@file2.puts "'Jane C. Doe'|'555-000-1234'"
-  @@file2.rewind
-
-  @@file3 = Tempfile.new('file3')
-  @@file3.puts "John Doe;555-123-4567;Good\tdude"
-  @@file3.puts "Jane C. Doe;555-000-1234   ; Great gal"
-  @@file3.puts "John Smith;555-999-1234;Don't know about him"
-  @@file3.rewind
-
-  @@file4 = Tempfile.new('file4')
-  @@file4.puts "Doe, John\t555-123-4567"
-  @@file4.puts "Jane C. Doe\t555-000-1234\t"
-  @@file4.rewind
-
-  @@file5 = Tempfile.new('file5')
-  @@file5.puts '"Doe,,,,,, John"|"555-123-4567"'
-  @@file5.puts '"Jane C. Doe"|"555-000-1234\t"'
-  @@file5.rewind
-
-  @@file6 = Tempfile.new('file6')
-  @@file6.puts 'Name|Phone No.|Age'
-  @@file6.puts 'Doe, John|555-123-4567|31'
-  @@file6.puts 'Doe, Jane C. |555-000-1234|30'
-  @@file6.rewind
-
-  def test_file1
-    assert_equal ",", CsvSniffer.detect_delimiter(@@file1.path)
-    assert_equal false, CsvSniffer.is_quote_enclosed?(@@file1.path)
-    assert_equal nil, CsvSniffer.get_quote_char(@@file1.path)
-    assert_equal true, CsvSniffer.has_header?(@@file1.path)
-  end
-
-  def test_file2
-    assert_equal "|", CsvSniffer.detect_delimiter(@@file2.path)
-    assert_equal true, CsvSniffer.is_quote_enclosed?(@@file2.path)
-    assert_equal "'", CsvSniffer.get_quote_char(@@file2.path)
-    assert_equal true, CsvSniffer.has_header?(@@file2.path)
-  end
-
-  def test_file3
-    assert_equal ";", CsvSniffer.detect_delimiter(@@file3.path)
-    assert_equal false, CsvSniffer.is_quote_enclosed?(@@file3.path)
-    assert_equal false, CsvSniffer.has_header?(@@file3.path)
-  end
-
-  def test_file4
-    assert_equal '\t', CsvSniffer.detect_delimiter(@@file4.path)
-    assert_equal nil, CsvSniffer.get_quote_char(@@file4.path)
-    assert_equal false, CsvSniffer.has_header?(@@file4.path)
-  end
-
-  def test_file5
-    assert_equal "|", CsvSniffer.detect_delimiter(@@file5.path)
-    assert_equal true, CsvSniffer.is_quote_enclosed?(@@file5.path)
-    assert_equal '"', CsvSniffer.get_quote_char(@@file5.path)
-  end
-
-  def test_file6
-    assert_equal "|", CsvSniffer.detect_delimiter(@@file6.path)
-    assert_equal true, CsvSniffer.has_header?(@@file6.path)
-  end
-
-end
+require 'minitest/autorun'
+require 'tempfile'
+require 'csv_sniffer'
+
+class CsvSnifferTest < Minitest::Test
+
+  @@file1 = Tempfile.new('file1')
+  @@file1.puts "Name,Number"
+  @@file1.puts "John Doe,555-123-4567"
+  @@file1.puts "Jane C. Doe,555-000-1234"
+  @@file1.rewind
+
+  @@file2 = Tempfile.new('file2')
+  @@file2.puts "'Name' |'Number'\t"
+  @@file2.puts "'John Doe'|'555-123-4567'"
+  @@file2.puts "'Jane C. Doe'|'555-000-1234'"
+  @@file2.rewind
+
+  @@file3 = Tempfile.new('file3')
+  @@file3.puts "John Doe;555-123-4567;Good\tdude"
+  @@file3.puts "Jane C. Doe;555-000-1234   ; Great gal"
+  @@file3.puts "John Smith;555-999-1234;Don't know about him"
+  @@file3.rewind
+
+  @@file4 = Tempfile.new('file4')
+  @@file4.puts "Doe, John\t555-123-4567"
+  @@file4.puts "Jane C. Doe\t555-000-1234\t"
+  @@file4.rewind
+
+  @@file5 = Tempfile.new('file5')
+  @@file5.puts '"Doe,,,,,, John"|"555-123-4567"'
+  @@file5.puts '"Jane C. Doe"|"555-000-1234\t"'
+  @@file5.rewind
+
+  @@file6 = Tempfile.new('file6')
+  @@file6.puts 'Name|Phone No.|Age'
+  @@file6.puts 'Doe, John|555-123-4567|31'
+  @@file6.puts 'Doe, Jane C. |555-000-1234|30'
+  @@file6.rewind
+
+  @@file7 = Tempfile.new('file7')
+  @@file7.rewind
+
+  def test_file1
+    assert_equal ",", CsvSniffer.detect_delimiter(@@file1.path)
+    assert_equal false, CsvSniffer.is_quote_enclosed?(@@file1.path)
+    assert_equal nil, CsvSniffer.get_quote_char(@@file1.path)
+    assert_equal true, CsvSniffer.has_header?(@@file1.path)
+  end
+
+  def test_file2
+    assert_equal "|", CsvSniffer.detect_delimiter(@@file2.path)
+    assert_equal true, CsvSniffer.is_quote_enclosed?(@@file2.path)
+    assert_equal "'", CsvSniffer.get_quote_char(@@file2.path)
+    assert_equal true, CsvSniffer.has_header?(@@file2.path)
+  end
+
+  def test_file3
+    assert_equal ";", CsvSniffer.detect_delimiter(@@file3.path)
+    assert_equal false, CsvSniffer.is_quote_enclosed?(@@file3.path)
+    assert_equal false, CsvSniffer.has_header?(@@file3.path)
+  end
+
+  def test_file4
+    assert_equal '\t', CsvSniffer.detect_delimiter(@@file4.path)
+    assert_equal nil, CsvSniffer.get_quote_char(@@file4.path)
+    assert_equal false, CsvSniffer.has_header?(@@file4.path)
+  end
+
+  def test_file5
+    assert_equal "|", CsvSniffer.detect_delimiter(@@file5.path)
+    assert_equal true, CsvSniffer.is_quote_enclosed?(@@file5.path)
+    assert_equal '"', CsvSniffer.get_quote_char(@@file5.path)
+  end
+
+  def test_file6
+    assert_equal "|", CsvSniffer.detect_delimiter(@@file6.path)
+    assert_equal true, CsvSniffer.has_header?(@@file6.path)
+  end
+
+  def test_file7
+    assert_equal false, CsvSniffer.has_header?(@@file7.path)
+    assert_equal nil, CsvSniffer.get_quote_char(@@file7.path)
+    assert_equal ",", CsvSniffer.detect_delimiter(@@file7.path)
+  end
+end

metadata

@@ -1,27 +1,27 @@
 --- !ruby/object:Gem::Specification
 name: csv_sniffer
 version: !ruby/object:Gem::Version
-  version: 0.1.1
+  version: 0.1.2
 platform: ruby
 authors:
 - Tim Ojo
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2015-10-16 00:00:00.000000000 Z
+date: 2015-12-28 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: test-unit
   requirement: !ruby/object:Gem::Requirement
     requirements:
-    - - '>='
+    - - "~>"
       - !ruby/object:Gem::Version
         version: '0'
   type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
-    - - '>='
+    - - "~>"
       - !ruby/object:Gem::Version
         version: '0'
 description: CSV Sniffer is a set of functions that allow a user detect the delimiter
@@ -33,6 +33,7 @@ executables: []
 extensions: []
 extra_rdoc_files: []
 files:
+- ".gitignore"
 - LICENSE
 - README.md
 - Rakefile
@@ -49,17 +50,17 @@ 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: 2.0.14
+rubygems_version: 2.4.7
 signing_key: 
 specification_version: 4
 summary: CSV library for heuristic detection of CSV properties