censive 0.8 → 0.9

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 6419efcdc9274ea8bcf7b8527001e33f8bdfea348dfd911686cab36984d507da
-  data.tar.gz: 3b59aead54517fd64d7ece3eaa6f459e301e1e48f1ae34772a7128c61fb739f2
+  metadata.gz: cbca33c415269ae1fafea5297f2b409879a46c37c884a0a7017bca322bcff2a6
+  data.tar.gz: ac021ddf3d7503aebc5791b0912c6409a0888627060b532e65f6eb72b94965a3
 SHA512:
-  metadata.gz: 7910c09e76a81ed27870ea52fb6c8aea0316ed213c53a026d98adc64f93349477e6acab0a93b88c6f184ce1d317634ecdca9290d50bff9b117b98bedd3ac7b86
-  data.tar.gz: 358ab985947d486b5f486b1f7e9c1f591e3b8e906b9eab59a4ed151e5f5d9652c211f2d2a4ee36f0543227e2ae5e33ba57f1e4c178f6f7e72e05c14d7b46895f
+  metadata.gz: 8095c0c7704e3a6ee66930b36f0131b38d52a68cdd066d9677e8ceb58c4ecd7ce7eed496c78b1841cabe845b8c82624ca808b33a7cf7ec4c8fd504b287b3ffb5
+  data.tar.gz: 2e363b63b37977784a38c06e091f3201a1cd7a13138e8101e0e41ca49c47b3c4b433e7e6f2843a6816ddcbf9c1c8293da0d858f6be38bd0d3d82ed5dbd904bfe

data/README.md

@@ -12,7 +12,7 @@ data = File.read('data.csv')
 
 # write out a tab-separated tsv file
 Censive.writer('out.tsv', sep: "\t", mode: :full) do |out|
-  Censive.new(data).each do |row|
+  Censive.new(data, excel: true, relax: true).each do |row|
     out << row
   end
 end

data/censive.gemspec

@@ -2,7 +2,7 @@
 
 Gem::Specification.new do |s|
   s.name        = "censive"
-  s.version     = "0.8"
+  s.version     = "0.9"
   s.author      = "Steve Shreeve"
   s.email       = "steve.shreeve@gmail.com"
   s.summary     = "A quick and lightweight CSV handling library for Ruby"

data/lib/censive.rb

@@ -6,7 +6,8 @@
 # Author: Steve Shreeve (steve.shreeve@gmail.com)
 #   Date: Jan 30, 2023
 #
-# Thanks: Crystal's CSV library, see https://crystal-lang.org/api/1.7.2/CSV.html
+# Thanks to https://crystal-lang.org/api/1.7.2/CSV.html (Crystal's CSV library)
+# and, also https://github.com/ruby/strscan/blob/master/ext/strscan/strscan.c
 # ==============================================================================
 # The goals are:
 #
@@ -17,7 +18,8 @@
 #
 # 1. Option to support IO streaming
 # 2. Option to strip whitespace
-# 3. Confirm file encodings such as UTF-8, UTF-16, etc.
+# 3. Option to support headers in readers and writers
+# 4. Confirm file encodings such as UTF-8, UTF-16, etc.
 #
 # NOTE: Only getch and scan_until advance strscan's position
 # ==============================================================================
@@ -38,7 +40,7 @@ class Censive < StringScanner
 
     drop:  false   , # enable to drop trailing separators
     eol:   "\n"    , # desired line endings for exports
-    excel: false   , # allow ,="0123" style columns
+    excel: false   , # literals (="01"), formulas (=A1 + B2), see http://bit.ly/3Y7jIvc
     mode:  :compact, # export mode: compact or full
     out:   nil     , # output IO/file
     relax: false   , # relax parsing of quotes
@@ -53,6 +55,7 @@ class Censive < StringScanner
 
     @drop   = drop
     @eol    = eol.freeze
+    @excel  = excel
     @mode   = mode
     @out    = out
     @relax  = relax
@@ -64,7 +67,6 @@ class Censive < StringScanner
     @esc    = (@quote * 2).freeze
 
     @tokens = [@sep,@quote,@cr,@lf,@es,nil]
-    @tokens << @eq if excel # See http://bit.ly/3Y7jIvc
   end
 
   def reset(str=nil)
@@ -85,19 +87,27 @@ class Censive < StringScanner
   end
 
   def next_token
+
+    # process and clear @flag
     case @flag
     when @es then @flag = nil; [@cr,@lf,@es,nil].include?(@char) and return @es
     when @cr then @flag = nil; next_char == @lf and next_char
     when @lf then @flag = nil; next_char
+    else          @flag = nil
     end if @flag
 
+    # See http://bit.ly/3Y7jIvc
+    if @excel && @char == @eq
+      @flag = @eq
+      next_char
+    end
+
     if @tokens.include?(@char)
       case @char
-      when @quote, @eq # consume quoted cell
-        @char == @eq and next_char # excel mode: allows ,="012",
+      when @quote # consume quoted cell
         match = ""
         while true
-          getch # consume the quote (optimized by not calling next_char)
+          getch # consume the quote that got us here
           match << (scan_until(/(?=#{@quote})/o) or bomb "unclosed quote")
           case next_char
           when @sep            then @flag = @es; next_char; break
@@ -119,6 +129,7 @@ class Censive < StringScanner
       end
     else # consume unquoted cell
       match = scan_until(/(?=#{@sep}|#{@cr}|#{@lf}|\z)/o) or bomb "unexpected character"
+      match = @eq + match if @flag == @eq # preserve @eq for excel formulas
       @char = peek(1)
       @char == @sep and @flag = @es and next_char
       match
@@ -151,9 +162,9 @@ class Censive < StringScanner
 
   # ==[ Helpers ]==
 
-  # grok returns: 2 for seps and quotes, 1 for seps only, and 0 for neither
+  # grok returns: 2 (must be quoted and escaped), 1 (must be quoted), 0 (neither)
   def grok(str)
-    if pos = str.index(/(#{@quote})|#{@sep}/o)
+    if pos = str.index(/(#{@quote})|#{@sep}|#{@cr}|#{@lf}/o)
       $1 ? 2 : str.index(/#{@quote}/o, pos) ? 2 : 1
     else
       0
@@ -171,8 +182,12 @@ class Censive < StringScanner
     out = case @mode
     when :compact
       case grok(row.join)
-      when 0 then row
-      when 1 then row.map {|col| col.include?(s) ? "#{q}#{col}#{q}" : col }
+      when 0
+        row
+      when 1
+        row.map do |col|
+          col.match?(/#{@sep}|#{@cr}|#{@lf}/o) ? "#{q}#{col}#{q}" : col
+        end
       else
         row.map do |col|
           case grok(col)

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: censive
 version: !ruby/object:Gem::Version
-  version: '0.8'
+  version: '0.9'
 platform: ruby
 authors:
 - Steve Shreeve