censive 0.13 → 0.15

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: f3d6b5bd88adf5c40972cd5a978b49e57a7a8724780eeaaf80b0cb749323dc1d
-  data.tar.gz: c24b0efa60901ca6d8de7e8314a3b137c981601b866d837123a96722acf826db
+  metadata.gz: 4211eb0036bcbadf9d1683f10084bb8cbb109d26845d6990778e159b634b8d00
+  data.tar.gz: 1f97a3e5343958a86d54b7f1f87ada5d05a8f091d597253c3079c1a15eeb4dfa
 SHA512:
-  metadata.gz: 3584864597a1631179212563d29ad188a55c2ed90dd1d36c6464e641ee6b5a85c01437516cdf2865c39e9f4f9bfc96605ae318ca456d722afc544e31d87e1801
-  data.tar.gz: a7c59e427ca7014e0207dc8c3bb8eb1647c41f9193de021dc4a0ee98b913cfa54105f5bbf5301c2ec852feace0ed7d69622008acc2c09697b5ab1e9560fd89d3
+  metadata.gz: f3b8e0ee3cf2d8eadbb26d6be5b590418a844561062779f47eec0863b87cfbc65868a8c89624865eb74ee7f6825ee3fb1d2d26611353a30f805d40d567c1f1ac
+  data.tar.gz: 949e07f3f2208cbecc868a85c7bde5e67f38bf570ae1708496fd7745703c3fc133e8d48fc03c5c18c85264c0bff5b394d5ce2c2b2894daa8b7ca9033f9d68828

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     = "0.15"
   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

@@ -4,25 +4,21 @@
 # censive - A quick and lightweight CSV handling library for Ruby
 #
 # Author: Steve Shreeve (steve.shreeve@gmail.com)
-#   Date: Feb 3, 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
-# 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"
 require "strscan"
 
 class Censive < StringScanner
@@ -36,83 +32,71 @@ 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
-    **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
-
-    @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 = curr_char
     @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
-    end
+    excel = true if @excel && scan(@eq)
 
-    if @char == @quote # consume quoted cell
-      match = ""
+    if scan(@quote) # consume quoted cell
+      token = ""
       while true
-        next_char
-        match << (scan_until(/(?=#{@quote})/o) or bomb "unclosed quote")
-        match << @quote and next if next_char == @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"
-        match << @quote + scan_until(/(?=#{@quote})/o) + @quote
-      end
-      next_char if @char == @sep
-      match
-    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
+        quoted = scan_until(/#{@quote}/o) or bomb "invalid inline quote"
+        token << @quote + quoted + @quote
       end
+    elsif scan(@sep) then return @es
+    elsif scan(@eol) then return nil
     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(@eoc) or bomb "unexpected character"
+      token.prepend(@eq) if excel
     end
+    scan(@sep)
+    @strip ? token.strip : token
   end
 
   def bomb(msg)
@@ -143,7 +127,7 @@ 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 +148,7 @@ 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|
@@ -186,7 +170,7 @@ class Censive < StringScanner
       end
     end.join(s)
 
-    @out << out + @eol
+    @out << out + @rowsep
   end
 
   def each

metadata

@@ -1,29 +1,15 @@
 --- !ruby/object:Gem::Specification
 name: censive
 version: !ruby/object:Gem::Version
-  version: '0.13'
+  version: '0.15'
 platform: ruby
 authors:
 - Steve Shreeve
 autorequire:
 bindir: bin
 cert_chain: []
-date: 2023-02-04 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
+date: 2023-02-05 00:00:00.000000000 Z
+dependencies: []
 description: A quick and lightweight CSV handling library for Ruby
 email: steve.shreeve@gmail.com
 executables: []