censive 0.14 → 0.16

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: '072390db5028d3fc9f2bf9c22f95616dea749a502c6f010c25f222f0f8bd86ec'
-  data.tar.gz: 012b5549ca2454f22db2b5bdc225e4a703c622d6a636ddea2f31bd6380556164
+  metadata.gz: 7abd1490426ab80b6b1cc3c7b28a590eb22c5dd565405662dd82bd1c427b013b
+  data.tar.gz: adb90312a493b92ccb36e7354153a30f530f33d2b205fd6ebbea49ca1e80efe5
 SHA512:
-  metadata.gz: 285efce01bbdee5e2f2505757342de56918025a2f2a146e1ec5ba9677a2c27cb8698ef0e68170fdeb74cf7e7a82665ea7e533732b813a8c39680bff7c3c22674
-  data.tar.gz: 0f36dcba5cac1f608db296fa1728dc87fc50134d1d356bc1d699533c75b02c8eb4dcfa5b33326b68d78f4bb9edaff39d7da975c04eaa6549b1536e2e113bbb61
+  metadata.gz: f603db91e71cce8d72322d9a248f81f625238aa2a7d5107a6849d18ecdb00cf94865f2ad716afde1df79e4d0dd126765968822e3e9d53f3bea09886f2ae08d89
+  data.tar.gz: b5fc1fa9b2a309677091334d50200ada240ea2490d23d427cc32774a828a672ce1be1c22e156d21a7ef0ebdfc604f7b003386f46d4bc7fb2b6fdb50dc6d2a857

data/censive.gemspec

@@ -2,7 +2,7 @@
 
 Gem::Specification.new do |s|
   s.name        = "censive"
-  s.version     = "0.14"
+  s.version     = "0.16"
   s.author      = "Steve Shreeve"
   s.email       = "steve.shreeve@gmail.com"
   s.summary     =
@@ -11,5 +11,4 @@ Gem::Specification.new do |s|
   s.license     = "MIT"
   s.files       = `git ls-files`.split("\n") - %w[.gitignore]
   s.executables = `(cd bin 2>&1) > /dev/null && git ls-files .`.split("\n")
-  s.add_dependency "strscan", ">= 3.0.6"
 end

data/lib/censive.rb

@@ -4,12 +4,12 @@
 # censive - A quick and lightweight CSV handling library for Ruby
 #
 # Author: Steve Shreeve (steve.shreeve@gmail.com)
-#   Date: Feb 4, 2023
+#   Date: Feb 5, 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
-# https://github.com/ruby/strscan/issues/53 for details
-# https://github.com/ruby/strscan/pull/54 for code
+#
+# Thanks to Sutou Kouhei (kou) for his excellent advice on using scan
 # ============================================================================
 # GOALS:
 # 1. Faster than Ruby's default CSV library
@@ -19,7 +19,6 @@
 # TODO: Support IO streaming
 # ============================================================================
 
-require "bundler/setup"
 require "strscan"
 
 class Censive < StringScanner
@@ -33,41 +32,44 @@ class Censive < StringScanner
   end
 
   def initialize(str=nil,
-    drop:  false   , # drop trailing empty fields?
-    eol:   "\n"    , # line endings for exports
-    excel: false   , # literals ="01" formulas =A1 + B2 http://bit.ly/3Y7jIvc
-    mode:  :compact, # export mode: compact or full
-    out:   nil     , # output stream, needs to respond to <<
-    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
+    drop:   false   , # drop trailing empty fields?
+    excel:  false   , # literals ="01" formulas =A1 + B2 http://bit.ly/3Y7jIvc
+    mode:   :compact, # export mode: compact or full
+    out:    $stdout , # output stream, needs to respond to <<
+    quote:  '"'     , # quote character
+    relax:  false   , # relax quote parsing so ,"Fo"o, => ,"Fo""o",
+    rowsep: "\n"    , # row separator for export
+    sep:    ","     , # column separator character
+    strip:  false   , # strip fields when reading
+    **opts            # grab bag
   )
     super(str || "")
     reset
 
-    @drop   = drop
-    @eol    = eol
-    @excel  = excel
-    @mode   = mode
-    @out    = out || $stdout
-    @quote  = quote
-    @relax  = relax
-    @sep    = sep
-    @strip  = strip
-
-    @cr     = "\r"
-    @lf     = "\n"
-    @es     = ""
-    @eq     = "="
-    @esc    = (@quote * 2)
+    # options
+    @drop    = drop
+    @excel   = excel
+    @mode    = mode
+    @out     = out
+    @quote   = quote
+    @relax   = relax
+    @rowsep  = rowsep
+    @sep     = sep
+    @strip   = strip
+
+    # determined
+    @cr  = "\r"
+    @lf  = "\n"
+    @es  = ""
+    @eq  = "="
+    @esc = (@quote * 2)
+    @eol = /#{@cr}#{@lf}?|#{@lf}|\z/o             # end of line
+    @eoc = /(?=#{"\\" + @sep}|#{@cr}|#{@lf}|\z)/o # end of cell
   end
 
   def reset(str=nil)
     self.string = str if str
     super()
-    @char = currchar
     @rows = nil
     @cols = @cells = 0
   end
@@ -75,36 +77,25 @@ class Censive < StringScanner
   # ==[ Lexer ]==
 
   def next_token
-    if @excel && @char == @eq
-      excel = true
-      @char = nextchar
-    end
+    excel = true if @excel && scan(@eq)
 
-    if @char == @quote # consume quoted cell
+    if scan(@quote) # consume quoted cell
       token = ""
       while true
-        @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)
+        token << (scan_until(/#{@quote}/o) or bomb "unclosed quote")[0..-2]
+        token << @quote and next if scan(@quote)
+        break if scan(@eoc)
         @relax or bomb "invalid character after quote"
-        token << @quote + scan_until(/(?=#{@quote})/o) + @quote
-      end
-      @char = nextchar if @char == @sep
-      @strip ? token.strip : token
-    elsif [@sep,@cr,@lf,@es,nil].include?(@char)
-      case @char
-      when @sep then  @char = nextchar                             ; @es
-      when @cr  then (@char = nextchar) == @lf and @char = nextchar; nil
-      when @lf  then  @char = nextchar                             ; nil
-      else                                                           nil
+        token << @quote + (scan_until(/#{@quote}/o) or bomb "bad inline quote")
       end
+    elsif scan(@sep) then return @es
+    elsif scan(@eol) then return nil
     else # consume unquoted cell
-      token = scan_until(/(?=#{"\\"+@sep}|#{@cr}|#{@lf}|\z)/o) or bomb "unexpected character"
+      token = scan_until(@eoc) or bomb "unexpected character"
       token.prepend(@eq) if excel
-      @char = nextchar if (@char = currchar) == @sep
-      @strip ? token.strip : token
     end
+    scan(@sep)
+    @strip ? token.strip : token
   end
 
   def bomb(msg)
@@ -178,7 +169,7 @@ class Censive < StringScanner
       end
     end.join(s)
 
-    @out << out + @eol
+    @out << out + @rowsep
   end
 
   def each
@@ -201,14 +192,15 @@ class Censive < StringScanner
 end
 
 if __FILE__ == $0
-  raw = DATA.read
-# raw = DATA.gets("\n\n").chomp
+  raw = DATA.gets("\n\n").chomp
 # raw = File.read(ARGV.first || "lc-2023.csv")
-  csv = Censive.new(raw, excel: true, relax: true, strip: true)
-  csv.export(sep: "|", excel: true)
+  csv = Censive.new(raw, excel: true, relax: true)
+  csv.export # (sep: ",", excel: true)
 end
 
 __END__
+123,"CHO, JOELLE "JOJO"",456
+
 Name,Age,Shoe
 Alice,27,5
 Bob,33,10 1/2

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: censive
 version: !ruby/object:Gem::Version
-  version: '0.14'
+  version: '0.16'
 platform: ruby
 authors:
 - Steve Shreeve
@@ -9,21 +9,7 @@ autorequire:
 bindir: bin
 cert_chain: []
 date: 2023-02-05 00:00:00.000000000 Z
-dependencies:
-- !ruby/object:Gem::Dependency
-  name: strscan
-  requirement: !ruby/object:Gem::Requirement
-    requirements:
-    - - ">="
-      - !ruby/object:Gem::Version
-        version: 3.0.6
-  type: :runtime
-  prerelease: false
-  version_requirements: !ruby/object:Gem::Requirement
-    requirements:
-    - - ">="
-      - !ruby/object:Gem::Version
-        version: 3.0.6
+dependencies: []
 description: A quick and lightweight CSV handling library for Ruby
 email: steve.shreeve@gmail.com
 executables: []