dsv 0.12.6 → 0.12.7

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 7322674ac0843543bf2f813312290dd2c4d460c7c3d0e8e8d604ccfcb680a196
-  data.tar.gz: 866e0a95d7854265444854111c0f1b61ed5e0faf9eb1f55ba20061f60fe52447
+  metadata.gz: ac547ecbc72cfc0cfb3b4e2a1f9c0c5327ea1f4e064c126a28aa85f8c3a42ded
+  data.tar.gz: 5be7f5303ed207575c43dfacac8d7b4e68f259172b48d25aba60104af57b68f7
 SHA512:
-  metadata.gz: 219226e29fa873569b197d731813421aa478d18719bb25ede6501b84ab42efd574112a1131c7e3526933fe5099c8c1c3fffb8345d1fcdb26392dd8ef9fe445c9
-  data.tar.gz: e57b19a5fc7ce1855f4fd40cca7a496bd946464c43f84e00e13f8a3b031d2e8b7c104e6995e749d2955a968c941896d80951f8190f557ff17ea92734c65aba66
+  metadata.gz: 022fbe8f4caf5baf90c785ba1ef586574d270331e25b6734e1e982766e1a8836a3182f1f92452734ce1d3316e834e0b07da4b8f9b89f6105c45222e4505dab7b
+  data.tar.gz: 19cd8f16d5b72349be0e066f63a5dcbac7cc9ea1ab4736e67cd07507415794ce2f9cc47d9bc747358125c252480018b1a0170efd820bdab8056611f46971cfd0

data/CHANGELOG

@@ -2,6 +2,12 @@
 
 ## 20261027
 
+0.12.7: ~ reassemble_quoted_fields(): an escaped quote before a separator no longer closes a quoted field.
+
+1. ~ reassemble_quoted_fields(): a piece closes a field where it ends in an odd run of quotes; + trailing_quotes().
+2. ~ test/dsv_test.rb: - the skip on a doubled quote before a separator.
+3. ~ lib/DSV/VERSION.rb: /0.12.6/0.12.7/.
+
 0.12.6: + quoting examples.
 
 1. ~ test/dsv_test.rb: + a doubled quote before a separator, skipped; + a quote not opening a field read as data; + a stray quote not taking in the next line, skipped; + an unclosed quoted field raising UnterminatedQuote, skipped.

data/lib/DSV/VERSION.rb

@@ -2,5 +2,5 @@
 # DSV::VERSION
 
 class DSV
-  VERSION = '0.12.6'
+  VERSION = '0.12.7'
 end

data/lib/dsv.rb

@@ -332,19 +332,19 @@ class DSV
     )
   end
 
-  # Pieces of a row split on the separator, the pieces of a quoted field that held the separator joined back with it, or with the text it matched where the separator is a Regexp; a piece that is a lone quote opens or closes a field.
+  # Pieces of a row split on the separator, the pieces of a quoted field that held the separator joined back with it, or with the text it matched where the separator is a Regexp; a piece closes a field where it ends in an odd run of quotes, a doubled quote being escaped, and a piece that is a lone quote opens or closes one.
   def reassemble_quoted_fields(pieces, separators = nil)
     fields = []
     buffer = nil
     pieces.each_with_index do |piece, i|
-      if buffer && !piece.end_with?('"')
+      if buffer && trailing_quotes(piece, -1).even?
         buffer << separator_before(i, separators) << piece
       elsif buffer
         fields << (buffer << separator_before(i, separators) << piece.delete_suffix('"')).gsub('""', '"')
         buffer = nil
-      elsif piece.start_with?('"') && (piece.length == 1 || !piece.end_with?('"'))
+      elsif piece.start_with?('"') && trailing_quotes(piece, 0).even?
         buffer = +piece.delete_prefix('"')
-      elsif piece.start_with?('"') && piece.end_with?('"')
+      elsif piece.start_with?('"')
         fields << piece.delete_prefix('"').delete_suffix('"').gsub('""', '"')
       else
         fields << piece
@@ -353,6 +353,13 @@ class DSV
     fields
   end
 
+  # How many quotes a piece ends with, counting back to but not including the byte given, so that a field's opening quote is not taken for part of its closing. Read by byte, a quote being 34 in any ASCII-compatible encoding, so that nothing is allocated per character.
+  def trailing_quotes(piece, floor)
+    i = piece.bytesize - 1
+    i -= 1 while i > floor && piece.getbyte(i) == 34
+    piece.bytesize - 1 - i
+  end
+
   # What stood between a piece and the one before it: the separator, or the text a Regexp separator matched there.
   def separator_before(i, separators)
     separators ? separators[i - 1] : @column_separator

data/test/dsv_test.rb

@@ -243,7 +243,6 @@ describe DSV do
     end
 
     it "reads a doubled quote just before a separator inside a quoted field" do
-      skip "Observation: a piece of a quoted field ending in a quote is taken as the field's end, an escaped quote ending in one as a closing quote does"
       _(DSV.parse_line('"He said ""no"", then left",x')).must_equal ['He said "no", then left', 'x']
       _(DSV.parse_line('"a"",""b",c')).must_equal ['a","b', 'c']
       _(DSV.read("\"a\"\",\"\"b\",\"c\"\n", quote: :double)).must_equal [{0 => 'a","b', 1 => 'c'}]

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: dsv
 version: !ruby/object:Gem::Version
-  version: 0.12.6
+  version: 0.12.7
 platform: ruby
 authors:
 - thoran