csvreader 1.2.1 → 1.2.5

data/test/test_parser_java.rb

@@ -1,208 +1,208 @@
-# encoding: utf-8
-
-###
-#  to run use
-#     ruby -I ./lib -I ./test test/test_parser_java.rb
-
-
-require 'helper'
-
-##########################
-# try some tests from apache java (commons) csv reader
-#  see https://github.com/apache/commons-csv/blob/master/src/test/java/org/apache/commons/csv/LexerTest.java
-
-
-class TestParserJava < MiniTest::Test
-
-
-LF	= "\n"     ##   \n == ASCII 0x0A (hex) 10 (dec) = LF (Newline/line feed)
-CR	= "\r"     ##   \r == ASCII 0x0D (hex) 13 (dec) = CR (Carriage return)
-
-
-
-def parser
-  CsvReader::Parser
-end
-
-def test_surrounding_spaces_are_deleted
-  assert_equal [["noSpaces",
-                 "leadingSpaces",
-                 "trailingSpaces",
-                 "surroundingSpaces",
-                 "",
-                 "",
-                 ""]], parser.default.parse( "noSpaces,  leadingSpaces,trailingSpaces  ,  surroundingSpaces  ,  ,," )
-end
-
-
-def test_surrounding_tabs_are_deleted
-  assert_equal [["noTabs",
-                 "leadingTab",
-                 "trailingTab",
-                 "surroundingTabs",
-                 "",
-                 "",
-                 ""]], parser.default.parse( "noTabs,\tleadingTab,trailingTab\t,\tsurroundingTabs\t,\t\t,," )
-end
-
-def test_ignore_empty_lines
-  assert_equal [[ "first", "line", "" ],
-                [ "second", "line" ],
-                [ "third line" ],
-                [ "last", "line" ]],
-                parser.default.parse( "first,line,\n" + "\n" + "\n" +
-                              "second,line\n" + "\n" + "\n" +
-                              "third line \n" + "\n" + "\n" +
-                              "last, line \n" + "\n" + "\n" + "\n" )
-end
-
-
-def test_comments
-  assert_equal [["first",  "line", "" ],
-                ["second", "line", "tokenWith#no-comment" ],
-                ["third",  "line", "#no-comment" ]],
-                parser.default.parse( "first,line,\n" +
-                              "second,line,tokenWith#no-comment\n" +
-                              "# comment line \n" +
-                              "third,line,#no-comment\n" +
-                              "# penultimate comment\n" +
-                              "# Final comment\n" )
-end
-
-
-
-
-
-def test_comments_and_empty_lines
-  parser.strict.comment = '#'
-
-  assert_equal [[ "1", "2", "3", "" ], ## 1
-                [ "" ], ## 1b
-                [ "" ], ## 1c
-                [ "a", "b x", "c#no-comment" ], ## 2
-                [ "" ],  ## 4
-                [ "" ],  ## 4b
-                [ "d", "e", "#no-comment" ], ## 5
-                [ "" ], ## 5b
-                [ "" ], ## 5c
-                [ "" ], ## 6b
-                [ "" ]  ## 6c
-               ],
-               parser.strict.parse(
-                  "1,2,3,\n" + ## 1
-                  "\n" +       ## 1b
-                  "\n" +       ## 1c
-                  "a,b x,c#no-comment\n" + ## 2
-                  "#foo\n" + ## 3
-                  "\n" + ## 4
-                  "\n" + ## 4b
-                  "d,e,#no-comment\n" + ## 5
-                  "\n" + ## 5b
-                  "\n" + ## 5c
-                  "# penultimate comment\n" + ## 6
-                  "\n" + ## 6b
-                  "\n" + ## 6c
-                  "# Final comment\n" ## 7
-              )
-
-  parser.strict.comment = false    ## reset to defaults
-end
-
-
-def test_backslash_with_escaping
-  ## simple token with escaping enabled
-  assert_equal [[ "a", ",", "b\\" ],
-                [ ",", "\nc", "d\r" ],
-                [ "e" ]], parser.default.parse( "a,\\,,b\\\\\n" +
-                                                "\\,,\\\nc,d\\\r\n" +
-                                                "e" )
-
-
-  parser.strict.escape = "\\"
-  assert_equal [[ "a", ",", "b\\" ],
-                [ ",", "\nc", "d\r" ],
-                [ "e" ]], parser.strict.parse( "a,\\,,b\\\\\n" +
-                                               "\\,,\\\nc,d\\\r\n" +
-                                               "e" )
-  parser.strict.escape = false
-end
-
-
-def test_backslash_without_escaping
-  ## simple token with escaping not enabled
-  assert_equal [[ "a",
-                  "\\", ## an unquoted single backslash is not an escape char
-                  "",
-                  "b\\" ## an unquoted single backslash is not an escape char
-                ],
-                [ "\\", "", "" ]], parser.strict.parse( "a,\\,,b\\\n" +
-                                                        "\\,," )
-
-end
-
-
-
-def test_next_token4
-  ## encapsulator tokenizer (single line)
-  assert_equal [[ "a", "foo", "b" ],
-                [ "a", " foo", "b" ],
-                [ "a", "foo ", "b" ],
-                [ "a", " foo ", "b" ]],
-                parser.default.parse( "a,\"foo\",b\n" +
-                                      "a,   \" foo\",b\n" +
-                                      "a,\"foo \"  ,b\n" +
-                                      "a,  \" foo \"  ,b" )
-end
-
-
-def test_next_token5
-    ## encapsulator tokenizer (multi line, delimiter in string)
-   assert_equal [[ "a", "foo\n", "b" ],
-                 [ "foo\n  baar ,,," ],
-                 [ "\n\t \n" ]],
-                 parser.default.parse( "a,\"foo\n\",b\n" +
-                                       "\"foo\n  baar ,,,\"\n" +
-                                       "\"\n\t \n\"" )
-end
-
-
-def test_separator_is_tab
-  parser.strict.sep = "\t"
-  assert_equal [["one",
-                 "two",
-                 "",
-                 "four ",
-                 " five",
-                 " six" ]], parser.strict.parse( "one\ttwo\t\tfour \t five\t six" )
-  parser.strict.sep = ","   ## reset back to comma
-end
-
-
-
-
-def test_escaped_cr
-    assert_equal [[ "character" + CR + "Escaped" ]],
-                 parser.default.parse( "character\\" + CR + "Escaped" )
-end
-
-
-def test_cr
-   assert_equal [[ "character"  ],
-                 [ "NotEscaped" ]],
-                parser.default.parse( "character" + CR + "NotEscaped" )
-end
-
-
-
-def test_escaped_lf
-    assert_equal [[ "character" + LF + "Escaped" ]],
-                 parser.default.parse( "character\\" + LF + "Escaped" )
-end
-
-def test_lf
-   assert_equal [[ "character" ],
-                 [ "NotEscaped" ]],
-                 parser.default.parse( "character" + LF + "NotEscaped" )
-end
-
-end # class TestParserJava
+# encoding: utf-8
+
+###
+#  to run use
+#     ruby -I ./lib -I ./test test/test_parser_java.rb
+
+
+require 'helper'
+
+##########################
+# try some tests from apache java (commons) csv reader
+#  see https://github.com/apache/commons-csv/blob/master/src/test/java/org/apache/commons/csv/LexerTest.java
+
+
+class TestParserJava < MiniTest::Test
+
+
+LF	= "\n"     ##   \n == ASCII 0x0A (hex) 10 (dec) = LF (Newline/line feed)
+CR	= "\r"     ##   \r == ASCII 0x0D (hex) 13 (dec) = CR (Carriage return)
+
+
+
+def parser
+  CsvReader::Parser
+end
+
+def test_surrounding_spaces_are_deleted
+  assert_equal [["noSpaces",
+                 "leadingSpaces",
+                 "trailingSpaces",
+                 "surroundingSpaces",
+                 "",
+                 "",
+                 ""]], parser.default.parse( "noSpaces,  leadingSpaces,trailingSpaces  ,  surroundingSpaces  ,  ,," )
+end
+
+
+def test_surrounding_tabs_are_deleted
+  assert_equal [["noTabs",
+                 "leadingTab",
+                 "trailingTab",
+                 "surroundingTabs",
+                 "",
+                 "",
+                 ""]], parser.default.parse( "noTabs,\tleadingTab,trailingTab\t,\tsurroundingTabs\t,\t\t,," )
+end
+
+def test_ignore_empty_lines
+  assert_equal [[ "first", "line", "" ],
+                [ "second", "line" ],
+                [ "third line" ],
+                [ "last", "line" ]],
+                parser.default.parse( "first,line,\n" + "\n" + "\n" +
+                              "second,line\n" + "\n" + "\n" +
+                              "third line \n" + "\n" + "\n" +
+                              "last, line \n" + "\n" + "\n" + "\n" )
+end
+
+
+def test_comments
+  assert_equal [["first",  "line", "" ],
+                ["second", "line", "tokenWith#no-comment" ],
+                ["third",  "line" ]],
+                parser.default.parse( "first,line,\n" +
+                              "second,line,tokenWith#no-comment\n" +
+                              "# comment line \n" +
+                              "third,line  #inline-end-of-line-comment\n" +
+                              "# penultimate comment\n" +
+                              "# Final comment\n" )
+end
+
+
+
+
+
+def test_comments_and_empty_lines
+  parser.strict.comment = '#'
+
+  assert_equal [[ "1", "2", "3", "" ], ## 1
+                [ "" ], ## 1b
+                [ "" ], ## 1c
+                [ "a", "b x", "c#no-comment" ], ## 2
+                [ "" ],  ## 4
+                [ "" ],  ## 4b
+                [ "d", "e", "#no-comment" ], ## 5
+                [ "" ], ## 5b
+                [ "" ], ## 5c
+                [ "" ], ## 6b
+                [ "" ]  ## 6c
+               ],
+               parser.strict.parse(
+                  "1,2,3,\n" + ## 1
+                  "\n" +       ## 1b
+                  "\n" +       ## 1c
+                  "a,b x,c#no-comment\n" + ## 2
+                  "#foo\n" + ## 3
+                  "\n" + ## 4
+                  "\n" + ## 4b
+                  "d,e,#no-comment\n" + ## 5
+                  "\n" + ## 5b
+                  "\n" + ## 5c
+                  "# penultimate comment\n" + ## 6
+                  "\n" + ## 6b
+                  "\n" + ## 6c
+                  "# Final comment\n" ## 7
+              )
+
+  parser.strict.comment = false    ## reset to defaults
+end
+
+
+def test_backslash_with_escaping
+  ## simple token with escaping enabled
+  assert_equal [[ "a", ",", "b\\" ],
+                [ ",", "\nc", "d\r" ],
+                [ "e" ]], parser.default.parse( "a,\\,,b\\\\\n" +
+                                                "\\,,\\\nc,d\\\r\n" +
+                                                "e" )
+
+
+  parser.strict.escape = "\\"
+  assert_equal [[ "a", ",", "b\\" ],
+                [ ",", "\nc", "d\r" ],
+                [ "e" ]], parser.strict.parse( "a,\\,,b\\\\\n" +
+                                               "\\,,\\\nc,d\\\r\n" +
+                                               "e" )
+  parser.strict.escape = false
+end
+
+
+def test_backslash_without_escaping
+  ## simple token with escaping not enabled
+  assert_equal [[ "a",
+                  "\\", ## an unquoted single backslash is not an escape char
+                  "",
+                  "b\\" ## an unquoted single backslash is not an escape char
+                ],
+                [ "\\", "", "" ]], parser.strict.parse( "a,\\,,b\\\n" +
+                                                        "\\,," )
+
+end
+
+
+
+def test_next_token4
+  ## encapsulator tokenizer (single line)
+  assert_equal [[ "a", "foo", "b" ],
+                [ "a", " foo", "b" ],
+                [ "a", "foo ", "b" ],
+                [ "a", " foo ", "b" ]],
+                parser.default.parse( "a,\"foo\",b\n" +
+                                      "a,   \" foo\",b\n" +
+                                      "a,\"foo \"  ,b\n" +
+                                      "a,  \" foo \"  ,b" )
+end
+
+
+def test_next_token5
+    ## encapsulator tokenizer (multi line, delimiter in string)
+   assert_equal [[ "a", "foo\n", "b" ],
+                 [ "foo\n  baar ,,," ],
+                 [ "\n\t \n" ]],
+                 parser.default.parse( "a,\"foo\n\",b\n" +
+                                       "\"foo\n  baar ,,,\"\n" +
+                                       "\"\n\t \n\"" )
+end
+
+
+def test_separator_is_tab
+  parser.strict.sep = "\t"
+  assert_equal [["one",
+                 "two",
+                 "",
+                 "four ",
+                 " five",
+                 " six" ]], parser.strict.parse( "one\ttwo\t\tfour \t five\t six" )
+  parser.strict.sep = ","   ## reset back to comma
+end
+
+
+
+
+def test_escaped_cr
+    assert_equal [[ "character" + CR + "Escaped" ]],
+                 parser.default.parse( "character\\" + CR + "Escaped" )
+end
+
+
+def test_cr
+   assert_equal [[ "character"  ],
+                 [ "NotEscaped" ]],
+                parser.default.parse( "character" + CR + "NotEscaped" )
+end
+
+
+
+def test_escaped_lf
+    assert_equal [[ "character" + LF + "Escaped" ]],
+                 parser.default.parse( "character\\" + LF + "Escaped" )
+end
+
+def test_lf
+   assert_equal [[ "character" ],
+                 [ "NotEscaped" ]],
+                 parser.default.parse( "character" + LF + "NotEscaped" )
+end
+
+end # class TestParserJava

metadata

@@ -1,59 +1,115 @@
 --- !ruby/object:Gem::Specification
 name: csvreader
 version: !ruby/object:Gem::Version
-  version: 1.2.1
+  version: 1.2.5
 platform: ruby
 authors:
 - Gerald Bauer
-autorequire: 
+autorequire:
 bindir: bin
 cert_chain: []
-date: 2018-11-06 00:00:00.000000000 Z
+date: 2021-10-05 00:00:00.000000000 Z
 dependencies:
+- !ruby/object:Gem::Dependency
+  name: tabreader
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: 1.0.1
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: 1.0.1
+- !ruby/object:Gem::Dependency
+  name: csvyaml
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: 0.1.0
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: 0.1.0
+- !ruby/object:Gem::Dependency
+  name: csvjson
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: 1.0.0
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: 1.0.0
 - !ruby/object:Gem::Dependency
   name: rdoc
   requirement: !ruby/object:Gem::Requirement
     requirements:
-    - - "~>"
+    - - ">="
       - !ruby/object:Gem::Version
         version: '4.0'
+    - - "<"
+      - !ruby/object:Gem::Version
+        version: '7'
   type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
-    - - "~>"
+    - - ">="
       - !ruby/object:Gem::Version
         version: '4.0'
+    - - "<"
+      - !ruby/object:Gem::Version
+        version: '7'
 - !ruby/object:Gem::Dependency
   name: hoe
   requirement: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '3.16'
+        version: '3.22'
   type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '3.16'
+        version: '3.22'
 description: csvreader - read tabular data in the comma-separated values (csv) format
   the right way (uses best practices out-of-the-box with zero-configuration)
 email: wwwmake@googlegroups.com
 executables: []
 extensions: []
 extra_rdoc_files:
-- HISTORY.md
-- LICENSE.md
+- CHANGELOG.md
 - Manifest.txt
 - README.md
 files:
-- HISTORY.md
-- LICENSE.md
+- CHANGELOG.md
 - Manifest.txt
 - README.md
 - Rakefile
+- datasets/beer.csv
+- datasets/beer11.csv
+- datasets/cars11.csv
+- datasets/cities11.csv
+- datasets/customers11.csv
+- datasets/iris.attrib.csv
+- datasets/iris11.csv
+- datasets/lcc.attrib.csv
+- datasets/shakespeare.csv
+- datasets/test.csv
 - lib/csvreader.rb
 - lib/csvreader/base.rb
 - lib/csvreader/buffer.rb
@@ -66,23 +122,15 @@ files:
 - lib/csvreader/parser_strict.rb
 - lib/csvreader/parser_tab.rb
 - lib/csvreader/parser_table.rb
+- lib/csvreader/parser_yaml.rb
 - lib/csvreader/reader.rb
 - lib/csvreader/reader_hash.rb
 - lib/csvreader/version.rb
-- test/data/beer.csv
-- test/data/beer11.csv
-- test/data/cars11.csv
-- test/data/cities11.csv
-- test/data/customers11.csv
-- test/data/iris.attrib.csv
-- test/data/iris11.csv
-- test/data/lcc.attrib.csv
-- test/data/shakespeare.csv
-- test/data/test.csv
 - test/helper.rb
 - test/test_buffer.rb
 - test/test_converter.rb
 - test/test_parser.rb
+- test/test_parser_autofix.rb
 - test/test_parser_directive.rb
 - test/test_parser_fixed.rb
 - test/test_parser_formats.rb
@@ -103,7 +151,7 @@ homepage: https://github.com/csvreader/csvreader
 licenses:
 - Public Domain
 metadata: {}
-post_install_message: 
+post_install_message:
 rdoc_options:
 - "--main"
 - README.md
@@ -120,9 +168,8 @@ required_rubygems_version: !ruby/object:Gem::Requirement
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
-rubyforge_project: 
-rubygems_version: 2.5.2
-signing_key: 
+rubygems_version: 3.1.4
+signing_key:
 specification_version: 4
 summary: csvreader - read tabular data in the comma-separated values (csv) format
   the right way (uses best practices out-of-the-box with zero-configuration)