dsv 0.12.5 → 0.12.7

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: d6c8309ce7e75acd45ed55995d9c1ef8f04f1c6e945e56e80cb60d1fe4b7fa2a
-  data.tar.gz: 2f6a5693d250797bf9e9ce69f2d06c2fd144e5722c7f3e7996c0f4029b71fdea
+  metadata.gz: ac547ecbc72cfc0cfb3b4e2a1f9c0c5327ea1f4e064c126a28aa85f8c3a42ded
+  data.tar.gz: 5be7f5303ed207575c43dfacac8d7b4e68f259172b48d25aba60104af57b68f7
 SHA512:
-  metadata.gz: c91f3fd66f79475ec7c617f47545378a08af49e3a78e7b52b684496b3ab6cb22205e2c26a5c7cd025ca26956ac8730685e2a4344ce7505ea4e46ef737ef0d7e5
-  data.tar.gz: 3b2c669417438150a4fdfe421358e75362148ac7fa4fe8be1579c79b4c0f7f862283a2797dbef5bd02949cf9218daa61cdc194c0ca84844f443d39242e937245
+  metadata.gz: 022fbe8f4caf5baf90c785ba1ef586574d270331e25b6734e1e982766e1a8836a3182f1f92452734ce1d3316e834e0b07da4b8f9b89f6105c45222e4505dab7b
+  data.tar.gz: 19cd8f16d5b72349be0e066f63a5dcbac7cc9ea1ab4736e67cd07507415794ce2f9cc47d9bc747358125c252480018b1a0170efd820bdab8056611f46971cfd0

data/CHANGELOG

@@ -1,5 +1,19 @@
 # dsv/CHANGELOG
 
+## 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.
+2. ~ lib/DSV/VERSION.rb: /0.12.5/0.12.6/.
+
+
 ## 20261016
 
 0.12.5: Regexp separators and quote: :double made to do what the README says.

data/lib/DSV/VERSION.rb

@@ -2,5 +2,5 @@
 # DSV::VERSION
 
 class DSV
-  VERSION = '0.12.5'
+  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

@@ -242,6 +242,12 @@ describe DSV do
       _(DSV.parse_line('foo,"""""",baz')).must_equal ['foo', '""', 'baz']
     end
 
+    it "reads a doubled quote just before a separator inside a quoted field" do
+      _(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'}]
+    end
+
     it "reads a trailing empty field as an empty string" do
       _(DSV.parse_line('foo,bar,')).must_equal ['foo', 'bar', '']
       _(DSV.parse_line(',')).must_equal ['', '']
@@ -548,6 +554,26 @@ describe DSV do
     end
   end
 
+  # Input which is not RFC 4180, read to one rule provisionally, until a policy for malformed quoting is decided: a quote is structure only where it opens a field, and a field it opens which does not close raises UnterminatedQuote.
+  describe "quoting on read, where the input is malformed" do
+    it "reads a quote which does not open a field as data" do
+      _(DSV.parse_line('a"b"c,d')).must_equal ['a"b"c', 'd']
+      _(DSV.parse_line('a, "b,c"')).must_equal ['a', ' "b', 'c"']
+    end
+
+    it "reads a stray quote in an unquoted field as data, without taking in the next line" do
+      skip "Observation: the quotes in a row are counted, so a stray quote leaves them unbalanced and the next line is taken into the row; unspecified since 0.11.4, :double since 0.12.5"
+      _(DSV.read("12\" pizza,9.99\nnext,row\n", as_array: true)).must_equal [['12" pizza', '9.99'], ['next', 'row']]
+      _(DSV.read("12\" pizza,9.99\nnext,row\n", as_array: true, quote: :double)).must_equal [['12" pizza', '9.99'], ['next', 'row']]
+    end
+
+    it "raises UnterminatedQuote on a quoted field which does not close" do
+      skip "Observation: a quoted field which does not close is dropped silently, with the rest of its row"
+      _{DSV.read("\"abc,d\n")}.must_raise DSV::UnterminatedQuote
+      _{DSV.read("\"ab\"c,d\n")}.must_raise DSV::UnterminatedQuote
+    end
+  end
+
   describe "#write" do
     it "writes each row in column order, double-quoted by default" do
       output = written(columns: [:a, :b]){|csv| csv.rows = [{'a' => 1, 'b' => 2}]; csv.write}

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: dsv
 version: !ruby/object:Gem::Version
-  version: 0.12.5
+  version: 0.12.7
 platform: ruby
 authors:
 - thoran