censive 0.13 → 0.14

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: f3d6b5bd88adf5c40972cd5a978b49e57a7a8724780eeaaf80b0cb749323dc1d
-  data.tar.gz: c24b0efa60901ca6d8de7e8314a3b137c981601b866d837123a96722acf826db
+  metadata.gz: '072390db5028d3fc9f2bf9c22f95616dea749a502c6f010c25f222f0f8bd86ec'
+  data.tar.gz: 012b5549ca2454f22db2b5bdc225e4a703c622d6a636ddea2f31bd6380556164
 SHA512:
-  metadata.gz: 3584864597a1631179212563d29ad188a55c2ed90dd1d36c6464e641ee6b5a85c01437516cdf2865c39e9f4f9bfc96605ae318ca456d722afc544e31d87e1801
-  data.tar.gz: a7c59e427ca7014e0207dc8c3bb8eb1647c41f9193de021dc4a0ee98b913cfa54105f5bbf5301c2ec852feace0ed7d69622008acc2c09697b5ab1e9560fd89d3
+  metadata.gz: 285efce01bbdee5e2f2505757342de56918025a2f2a146e1ec5ba9677a2c27cb8698ef0e68170fdeb74cf7e7a82665ea7e533732b813a8c39680bff7c3c22674
+  data.tar.gz: 0f36dcba5cac1f608db296fa1728dc87fc50134d1d356bc1d699533c75b02c8eb4dcfa5b33326b68d78f4bb9edaff39d7da975c04eaa6549b1536e2e113bbb61

data/README.md

@@ -74,6 +74,25 @@ Or, you can be more succinct with:
 ```ruby
 require 'censive'
 
-csv = Censive.new(File.read('data.csv'))
-csv.export(sep: "\t")
+csv = Censive.new(DATA.read, excel: true, relax: true, strip: true)
+csv.export(sep: "|", excel: true) # pipe separated, protect leading zeroes
+
+__END__
+Name,Age, Shoe
+  Alice,  27,5
+Bob,  33,10 1/2
+  Charlie or "Chuck",=B2 + B3,9
+"Doug E Fresh",="007",001122
+Subtotal,=sum(B2:B5),="01234"
+```
+
+Which returns:
+
+```
+Name|Age|Shoe
+Alice|27|5
+Bob|33|10 1/2
+"Charlie or ""Chuck"""|=B2 + B3|9
+Doug E Fresh|="007"|="001122"
+Subtotal|=sum(B2:B5)|="01234"
 ```

data/censive.gemspec

@@ -2,7 +2,7 @@
 
 Gem::Specification.new do |s|
   s.name        = "censive"
-  s.version     = "0.13"
+  s.version     = "0.14"
   s.author      = "Steve Shreeve"
   s.email       = "steve.shreeve@gmail.com"
   s.summary     =

data/lib/censive.rb

@@ -4,7 +4,7 @@
 # censive - A quick and lightweight CSV handling library for Ruby
 #
 # Author: Steve Shreeve (steve.shreeve@gmail.com)
-#   Date: Feb 3, 2023
+#   Date: Feb 4, 2023
 #
 # https://crystal-lang.org/api/1.7.2/CSV.html (Crystal's CSV library)
 # https://github.com/ruby/strscan/blob/master/ext/strscan/strscan.c
@@ -13,13 +13,10 @@
 # ============================================================================
 # GOALS:
 # 1. Faster than Ruby's default CSV library
-# 2. Lightweight code base with streamlined logic
-# 3. Support for most non-compliant CSV variations (eg - @relax, @excel)
+# 2. Lightweight code with streamlined and optimized logic
+# 3. Support most non-compliant CSV variations (eg - @excel, @relax, @strip)
 #
-# TODO:
-# 1. Support IO streaming
-# 2. Add option to strip whitespace
-# 3. Support CSV headers in first row
+# TODO: Support IO streaming
 # ============================================================================
 
 require "bundler/setup"
@@ -44,6 +41,7 @@ class Censive < StringScanner
     quote: '"'     , # quote character
     relax: false   , # relax quote parsing so ,"Fo"o, => ,"Fo""o",
     sep:   ","     , # column separator character
+    strip: false   , # strip fields when reading
     **opts           # grab bag
   )
     super(str || "")
@@ -57,6 +55,7 @@ class Censive < StringScanner
     @quote  = quote
     @relax  = relax
     @sep    = sep
+    @strip  = strip
 
     @cr     = "\r"
     @lf     = "\n"
@@ -68,50 +67,43 @@ class Censive < StringScanner
   def reset(str=nil)
     self.string = str if str
     super()
-    @char = curr_char
+    @char = currchar
     @rows = nil
     @cols = @cells = 0
   end
 
   # ==[ Lexer ]==
 
-  # pure ruby versions for debugging
-  # def curr_char;             @char = string[pos]; end
-  # def next_char; scan(/./m); @char = string[pos]; end
-
-  def curr_char; @char = currchar; end
-  def next_char; @char = nextchar; end
-
   def next_token
     if @excel && @char == @eq
       excel = true
-      next_char
+      @char = nextchar
     end
 
     if @char == @quote # consume quoted cell
-      match = ""
+      token = ""
       while true
-        next_char
-        match << (scan_until(/(?=#{@quote})/o) or bomb "unclosed quote")
-        match << @quote and next if next_char == @quote
+        @char = nextchar
+        token << (scan_until(/(?=#{@quote})/o) or bomb "unclosed quote")
+        token << @quote and next if (@char = nextchar) == @quote
         break if [@sep,@cr,@lf,@es,nil].include?(@char)
         @relax or bomb "invalid character after quote"
-        match << @quote + scan_until(/(?=#{@quote})/o) + @quote
+        token << @quote + scan_until(/(?=#{@quote})/o) + @quote
       end
-      next_char if @char == @sep
-      match
+      @char = nextchar if @char == @sep
+      @strip ? token.strip : token
     elsif [@sep,@cr,@lf,@es,nil].include?(@char)
       case @char
-      when @sep then next_char; @es
-      when @cr  then next_char == @lf and next_char; nil
-      when @lf  then next_char; nil
-      else nil
+      when @sep then  @char = nextchar                             ; @es
+      when @cr  then (@char = nextchar) == @lf and @char = nextchar; nil
+      when @lf  then  @char = nextchar                             ; nil
+      else                                                           nil
       end
     else # consume unquoted cell
-      match = scan_until(/(?=#{@sep}|#{@cr}|#{@lf}|\z)/o) or bomb "unexpected character"
-      match.prepend(@eq) if excel
-      next_char if curr_char == @sep
-      match
+      token = scan_until(/(?=#{"\\"+@sep}|#{@cr}|#{@lf}|\z)/o) or bomb "unexpected character"
+      token.prepend(@eq) if excel
+      @char = nextchar if (@char = currchar) == @sep
+      @strip ? token.strip : token
     end
   end
 
@@ -143,7 +135,7 @@ class Censive < StringScanner
 
   # returns 2 (must be quoted and escaped), 1 (must be quoted), 0 (neither)
   def grok(str)
-    if idx = str.index(/(#{@quote})|#{@sep}|#{@cr}|#{@lf}/o) #!# FIXME: regex injection?
+    if idx = str.index(/(#{@quote})|#{"\\"+@sep}|#{@cr}|#{@lf}/o)
       $1 ? 2 : str.index(/#{@quote}/o, idx) ? 2 : 1
     else
       0
@@ -164,7 +156,7 @@ class Censive < StringScanner
         row
       when 1
         row.map do |col|
-          col.match?(/#{@sep}|#{@cr}|#{@lf}/o) ? "#{q}#{col}#{q}" : col
+          col.match?(/#{"\\"+@sep}|#{@cr}|#{@lf}/o) ? "#{q}#{col}#{q}" : col
         end
       else
         row.map do |col|
@@ -209,10 +201,11 @@ class Censive < StringScanner
 end
 
 if __FILE__ == $0
-  raw = DATA.gets("\n\n").chomp
+  raw = DATA.read
+# raw = DATA.gets("\n\n").chomp
 # raw = File.read(ARGV.first || "lc-2023.csv")
-  csv = Censive.new(raw, excel: true, relax: true)
-  csv.export # (sep: ",", excel: true)
+  csv = Censive.new(raw, excel: true, relax: true, strip: true)
+  csv.export(sep: "|", excel: true)
 end
 
 __END__

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: censive
 version: !ruby/object:Gem::Version
-  version: '0.13'
+  version: '0.14'
 platform: ruby
 authors:
 - Steve Shreeve
 autorequire:
 bindir: bin
 cert_chain: []
-date: 2023-02-04 00:00:00.000000000 Z
+date: 2023-02-05 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: strscan