csv 3.2.7 → 3.2.9

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 6cc7b1ce29466412d00abcdb6afe594aa953f4b88367086398a3376484ca3344
-  data.tar.gz: b8112d963f92496cc775996c4e65d5b585601210fc03a4bc86eb4bf3c20e5f7d
+  metadata.gz: d7dabc413b85090aa7c9c93ca318de9adb1c0c2d94273f4e8d23d73d2882680a
+  data.tar.gz: 8e8484c342de0947a59af726ab20d7a88a2ae766a9e62139edb6c5650d144d0a
 SHA512:
-  metadata.gz: 3c29b38c150c691b52d0be24ab3dcdf32c430f2870de3ae4b26e704368caead83b27a581324a73515a85df8dc9571ab9f5fef1e8aa16a78f2ebfe3981a036063
-  data.tar.gz: 40cc68cb5a5eae059c3924e21e4fb53ae19e3c129f4b57e2bdcab35798742616daee93cf4bf9998de5333e03b01cc7b08a11da9700f04913a45f80741542d8f5
+  metadata.gz: 28edfb536bed667f78a618a3d13f5b305d1749879efae7256aaa8a0fa84694f2df7cc285851976b8b2f45ce9a7ae5741f9bd4277c3ea32c9a27fd2379a0f1be2
+  data.tar.gz: 7fe44532cde1e9022da25f798b696ad51b7c81bc3bd64cfd97610d13f073f141886bfdd03e9bb710bab2d3e7fda71a47cfea0ea7da8d3f6c06b38edfc295e364

data/NEWS.md

@@ -1,5 +1,37 @@
 # News
 
+## 3.2.9 - 2024-03-22
+
+### Fixes
+
+  * Fixed a parse bug that wrong result may be happen when:
+
+    * `:skip_lines` is used
+    * `:row_separator` is `"\r\n"`
+    * There is a line that includes `\n` as a column value
+
+    Reported by Ryo Tsukamoto.
+
+    GH-296
+
+### Thanks
+
+  * Ryo Tsukamoto
+
+## 3.2.8 - 2023-11-08
+
+### Improvements
+
+  * Added `CSV::InvalidEncodingError`.
+
+    Patch by Kosuke Shibata.
+
+    GH-287
+
+### Thanks
+
+  * Kosuke Shibata
+
 ## 3.2.7 - 2023-06-26
 
 ### Improvements

data/README.md

@@ -30,8 +30,8 @@ end
 
 ## Documentation
 
-- [API](https://ruby-doc.org/stdlib/libdoc/csv/rdoc/CSV.html):  all classes, methods, and constants.
-- [Recipes](https://ruby-doc.org/core/doc/csv/recipes/recipes_rdoc.html):  specific code for specific tasks.
+- [API](https://ruby.github.io/csv/):  all classes, methods, and constants.
+- [Recipes](https://ruby.github.io/csv/doc/csv/recipes/recipes_rdoc.html):  specific code for specific tasks.
 
 ## Development
 

data/lib/csv/parser.rb

@@ -220,6 +220,15 @@ class CSV
           end
           # trace(__method__, :repos, start, buffer)
           @scanner.pos = start
+          last_scanner, last_start, last_buffer = @keeps.last
+          # Drop the last buffer when the last buffer is the same data
+          # in the last keep. If we keep it, we have duplicated data
+          # by the next keep_back.
+          if last_scanner == @scanner and
+            last_buffer and
+            last_buffer == last_scanner.string.byteslice(last_start, start)
+            @keeps.last[2] = nil
+          end
         end
         read_chunk if @scanner.eos?
       end
@@ -414,8 +423,7 @@ class CSV
         else
           lineno = @lineno + 1
         end
-        message = "Invalid byte sequence in #{@encoding}"
-        raise MalformedCSVError.new(message, lineno)
+        raise InvalidEncodingError.new(@encoding, lineno)
       rescue UnexpectedError => error
         if @scanner
           ignore_broken_line
@@ -876,8 +884,7 @@ class CSV
               !line.valid_encoding?
             end
             if index
-              message = "Invalid byte sequence in #{@encoding}"
-              raise MalformedCSVError.new(message, @lineno + index + 1)
+              raise InvalidEncodingError.new(@encoding, @lineno + index + 1)
             end
           end
           Scanner.new(string)
@@ -894,18 +901,15 @@ class CSV
     def skip_needless_lines
       return unless @skip_lines
 
-      until @scanner.eos?
-        @scanner.keep_start
-        line = @scanner.scan_all(@not_line_end) || "".encode(@encoding)
+      @scanner.keep_start
+      @scanner.each_line(@row_separator) do |line|
         line << @row_separator if parse_row_end
-        if skip_line?(line)
-          @lineno += 1
-          @scanner.keep_drop
-        else
-          @scanner.keep_back
-          return
-        end
+        break unless skip_line?(line)
+        @lineno += 1
+        @scanner.keep_drop
+        @scanner.keep_start
       end
+      @scanner.keep_back
     end
 
     def skip_line?(line)

data/lib/csv/version.rb

@@ -2,5 +2,5 @@
 
 class CSV
   # The version of the installed library.
-  VERSION = "3.2.7"
+  VERSION = "3.2.9"
 end

data/lib/csv.rb

@@ -102,14 +102,6 @@ require_relative "csv/writer"
 
 # == \CSV
 #
-# === In a Hurry?
-#
-# If you are familiar with \CSV data and have a particular task in mind,
-# you may want to go directly to the:
-# - {Recipes for CSV}[doc/csv/recipes/recipes_rdoc.html].
-#
-# Otherwise, read on here, about the API: classes, methods, and constants.
-#
 # === \CSV Data
 #
 # \CSV (comma-separated values) data is a text representation of a table:
@@ -854,6 +846,15 @@ class CSV
     end
   end
 
+  # The error thrown when the parser encounters invalid encoding in CSV.
+  class InvalidEncodingError < MalformedCSVError
+    attr_reader :encoding
+    def initialize(encoding, line_number)
+      @encoding = encoding
+      super("Invalid byte sequence in #{encoding}", line_number)
+    end
+  end
+
   #
   # A FieldInfo Struct contains details about a field's position in the data
   # source it was read from.  CSV will pass this Struct to some blocks that make
@@ -1314,8 +1315,8 @@ class CSV
     #
     # Arguments:
     # * Argument +path_or_io+ must be a file path or an \IO stream.
-    # * Argument +mode+, if given, must be a \File mode
-    #   See {Open Mode}[https://ruby-doc.org/core/IO.html#method-c-new-label-Open+Mode].
+    # * Argument +mode+, if given, must be a \File mode.
+    #   See {Access Modes}[https://docs.ruby-lang.org/en/master/File.html#class-File-label-Access+Modes].
     # * Arguments <tt>**options</tt> must be keyword options.
     #   See {Options for Parsing}[#class-CSV-label-Options+for+Parsing].
     # * This method optionally accepts an additional <tt>:encoding</tt> option
@@ -1521,8 +1522,8 @@ class CSV
     #
     # * Argument +path+, if given, must be the path to a file.
     # :include: ../doc/csv/arguments/io.rdoc
-    # * Argument +mode+, if given, must be a \File mode
-    #   See {Open Mode}[IO.html#method-c-new-label-Open+Mode].
+    # * Argument +mode+, if given, must be a \File mode.
+    #   See {Access Modes}[https://docs.ruby-lang.org/en/master/File.html#class-File-label-Access+Modes].
     # * Arguments <tt>**options</tt> must be keyword options.
     #   See {Options for Generating}[#class-CSV-label-Options+for+Generating].
     # * This method optionally accepts an additional <tt>:encoding</tt> option

metadata

@@ -1,15 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: csv
 version: !ruby/object:Gem::Version
-  version: 3.2.7
+  version: 3.2.9
 platform: ruby
 authors:
 - James Edward Gray II
 - Kouhei Sutou
-autorequire:
 bindir: bin
 cert_chain: []
-date: 2023-06-26 00:00:00.000000000 Z
+date: 2024-03-22 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: bundler
@@ -128,7 +127,6 @@ licenses:
 - Ruby
 - BSD-2-Clause
 metadata: {}
-post_install_message:
 rdoc_options:
 - "--main"
 - README.md
@@ -145,8 +143,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
-rubygems_version: 3.5.0.dev
-signing_key:
+rubygems_version: 3.6.0.dev
 specification_version: 4
 summary: CSV Reading and Writing
 test_files: []