csvlint 1.0.0 → 1.2.0
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +4 -4
- data/.github/dependabot.yml +4 -0
- data/.github/workflows/push.yml +14 -2
- data/.pre-commit-hooks.yaml +5 -0
- data/.ruby-version +1 -1
- data/.standard_todo.yml +43 -0
- data/CHANGELOG.md +84 -32
- data/Dockerfile +16 -0
- data/Gemfile +2 -2
- data/README.md +30 -9
- data/Rakefile +7 -7
- data/csvlint.gemspec +14 -16
- data/docker_notes_for_windows.txt +20 -0
- data/features/step_definitions/cli_steps.rb +11 -11
- data/features/step_definitions/information_steps.rb +4 -4
- data/features/step_definitions/parse_csv_steps.rb +11 -11
- data/features/step_definitions/schema_validation_steps.rb +10 -10
- data/features/step_definitions/sources_steps.rb +1 -1
- data/features/step_definitions/validation_errors_steps.rb +19 -19
- data/features/step_definitions/validation_info_steps.rb +9 -9
- data/features/step_definitions/validation_warnings_steps.rb +11 -11
- data/features/support/aruba.rb +6 -6
- data/features/support/earl_formatter.rb +39 -39
- data/features/support/env.rb +10 -11
- data/features/support/load_tests.rb +107 -103
- data/features/support/webmock.rb +2 -2
- data/lib/csvlint/cli.rb +133 -130
- data/lib/csvlint/csvw/column.rb +279 -280
- data/lib/csvlint/csvw/date_format.rb +90 -92
- data/lib/csvlint/csvw/metadata_error.rb +1 -3
- data/lib/csvlint/csvw/number_format.rb +40 -32
- data/lib/csvlint/csvw/property_checker.rb +714 -717
- data/lib/csvlint/csvw/table.rb +49 -52
- data/lib/csvlint/csvw/table_group.rb +24 -23
- data/lib/csvlint/error_collector.rb +2 -0
- data/lib/csvlint/error_message.rb +0 -1
- data/lib/csvlint/field.rb +153 -141
- data/lib/csvlint/schema.rb +34 -42
- data/lib/csvlint/validate.rb +161 -143
- data/lib/csvlint/version.rb +1 -1
- data/lib/csvlint.rb +22 -23
- data/spec/csvw/column_spec.rb +15 -16
- data/spec/csvw/date_format_spec.rb +5 -7
- data/spec/csvw/number_format_spec.rb +2 -4
- data/spec/csvw/table_group_spec.rb +103 -105
- data/spec/csvw/table_spec.rb +71 -73
- data/spec/field_spec.rb +116 -121
- data/spec/schema_spec.rb +129 -139
- data/spec/spec_helper.rb +6 -6
- data/spec/validator_spec.rb +167 -190
- metadata +23 -55
@@ -1,6 +1,6 @@
|
|
1
|
-
require
|
2
|
-
require
|
3
|
-
require
|
1
|
+
require "json"
|
2
|
+
require "open-uri"
|
3
|
+
require "uri"
|
4
4
|
|
5
5
|
BASE_URI = "https://w3c.github.io/csvw/tests/"
|
6
6
|
BASE_PATH = File.join(File.dirname(__FILE__), "..", "fixtures", "csvw")
|
@@ -11,109 +11,113 @@ SCRIPT_FILE_PATH = File.join(File.dirname(__FILE__), "..", "..", "bin", "run-csv
|
|
11
11
|
Dir.mkdir(BASE_PATH) unless Dir.exist?(BASE_PATH)
|
12
12
|
|
13
13
|
def cache_file(filename)
|
14
|
-
|
15
|
-
|
16
|
-
|
17
|
-
|
18
|
-
|
19
|
-
|
20
|
-
|
21
|
-
|
22
|
-
|
23
|
-
|
24
|
-
|
25
|
-
|
26
|
-
f.puts URI.open(uri,
|
27
|
-
|
28
|
-
|
29
|
-
|
14
|
+
file = File.join(BASE_PATH, filename)
|
15
|
+
uri = URI.join(BASE_URI, filename)
|
16
|
+
unless File.exist?(file)
|
17
|
+
if filename.include? "/"
|
18
|
+
levels = filename.split("/")[0..-2]
|
19
|
+
for i in 0..levels.length
|
20
|
+
dir = File.join(BASE_PATH, levels[0..i].join("/"))
|
21
|
+
Dir.mkdir(dir) unless Dir.exist?(dir)
|
22
|
+
end
|
23
|
+
end
|
24
|
+
warn("storing #{file} locally")
|
25
|
+
File.open(file, "wb") do |f|
|
26
|
+
f.puts URI.open(uri, "rb").read
|
27
|
+
end
|
28
|
+
end
|
29
|
+
[uri, file]
|
30
30
|
end
|
31
31
|
|
32
|
-
File.
|
33
|
-
|
34
|
-
|
35
|
-
|
36
|
-
|
37
|
-
|
38
|
-
|
39
|
-
|
40
|
-
|
41
|
-
|
42
|
-
|
43
|
-
|
44
|
-
|
45
|
-
|
46
|
-
|
47
|
-
|
48
|
-
|
49
|
-
|
50
|
-
|
51
|
-
|
52
|
-
|
53
|
-
|
54
|
-
end
|
32
|
+
unless File.exist? SCRIPT_FILE_PATH
|
33
|
+
File.open(SCRIPT_FILE_PATH, "w") do |file|
|
34
|
+
File.chmod(0o755, SCRIPT_FILE_PATH)
|
35
|
+
manifest = JSON.parse(URI.open("#{BASE_URI}manifest-validation.jsonld").read)
|
36
|
+
manifest["entries"].each do |entry|
|
37
|
+
type = "valid"
|
38
|
+
case entry["type"]
|
39
|
+
when "csvt:WarningValidationTest"
|
40
|
+
type = "warnings"
|
41
|
+
when "csvt:NegativeValidationTest"
|
42
|
+
type = "errors"
|
43
|
+
end
|
44
|
+
file.puts "echo \"#{entry["id"].split("#")[-1]}: #{entry["name"].tr("`", "'")}\""
|
45
|
+
file.puts "echo \"#{type}: #{entry["comment"].gsub("\"", "\\\"").tr("`", "'")}\""
|
46
|
+
if entry["action"].end_with?(".json")
|
47
|
+
file.puts "csvlint --schema=features/fixtures/csvw/#{entry["action"]}"
|
48
|
+
elsif entry["option"] && entry["option"]["metadata"]
|
49
|
+
file.puts "csvlint features/fixtures/csvw/#{entry["action"]} --schema=features/fixtures/csvw/#{entry["option"]["metadata"]}"
|
50
|
+
else
|
51
|
+
file.puts "csvlint features/fixtures/csvw/#{entry["action"]}"
|
52
|
+
end
|
53
|
+
file.puts "echo"
|
54
|
+
end
|
55
|
+
end
|
56
|
+
end
|
55
57
|
|
56
|
-
File.
|
57
|
-
|
58
|
-
|
58
|
+
unless File.exist? VALIDATION_FEATURE_FILE_PATH
|
59
|
+
File.open(VALIDATION_FEATURE_FILE_PATH, "w") do |file|
|
60
|
+
file.puts "# Auto-generated file based on standard validation CSVW tests from #{BASE_URI}manifest-validation.jsonld"
|
61
|
+
file.puts ""
|
59
62
|
|
60
|
-
|
63
|
+
manifest = JSON.parse(URI.open("#{BASE_URI}manifest-validation.jsonld").read)
|
61
64
|
|
62
|
-
|
63
|
-
|
65
|
+
file.puts "Feature: #{manifest["label"]}"
|
66
|
+
file.puts ""
|
64
67
|
|
65
|
-
|
66
|
-
|
67
|
-
|
68
|
-
|
69
|
-
|
70
|
-
|
71
|
-
|
72
|
-
|
73
|
-
|
74
|
-
|
75
|
-
|
76
|
-
|
77
|
-
|
78
|
-
|
79
|
-
|
80
|
-
|
81
|
-
|
82
|
-
|
83
|
-
|
84
|
-
|
85
|
-
|
86
|
-
|
87
|
-
|
88
|
-
|
89
|
-
|
90
|
-
|
91
|
-
|
92
|
-
|
93
|
-
|
94
|
-
|
95
|
-
|
96
|
-
|
97
|
-
|
98
|
-
|
99
|
-
|
100
|
-
|
101
|
-
|
102
|
-
|
103
|
-
|
104
|
-
|
105
|
-
|
106
|
-
|
107
|
-
|
108
|
-
|
109
|
-
|
110
|
-
|
111
|
-
|
112
|
-
|
113
|
-
|
114
|
-
|
115
|
-
|
116
|
-
|
117
|
-
|
118
|
-
|
119
|
-
end
|
68
|
+
manifest["entries"].each do |entry|
|
69
|
+
action_uri, action_file = cache_file(entry["action"])
|
70
|
+
metadata = nil
|
71
|
+
provided_files = []
|
72
|
+
missing_files = []
|
73
|
+
file.puts "\t# #{entry["id"]}"
|
74
|
+
file.puts "\t# #{entry["comment"]}"
|
75
|
+
file.puts "\tScenario: #{entry["id"]} #{entry["name"].gsub("<", "less than")}"
|
76
|
+
if entry["action"].end_with?(".json")
|
77
|
+
file.puts "\t\tGiven I have a metadata file called \"csvw/#{entry["action"]}\""
|
78
|
+
file.puts "\t\tAnd the metadata is stored at the url \"#{action_uri}\""
|
79
|
+
else
|
80
|
+
file.puts "\t\tGiven I have a CSV file called \"csvw/#{entry["action"]}\""
|
81
|
+
file.puts "\t\tAnd it has a Link header holding \"#{entry["httpLink"]}\"" if entry["httpLink"]
|
82
|
+
file.puts "\t\tAnd it is stored at the url \"#{action_uri}\""
|
83
|
+
if entry["option"] && entry["option"]["metadata"]
|
84
|
+
# no need to store the file here, as it will be listed in the 'implicit' list, which all get stored
|
85
|
+
metadata = URI.join(BASE_URI, entry["option"]["metadata"])
|
86
|
+
file.puts "\t\tAnd I have a metadata file called \"csvw/#{entry["option"]["metadata"]}\""
|
87
|
+
file.puts "\t\tAnd the metadata is stored at the url \"#{metadata}\""
|
88
|
+
end
|
89
|
+
provided_files << action_uri.to_s
|
90
|
+
if entry["name"].include?("/.well-known/csvm")
|
91
|
+
file.puts "\t\tAnd I have a file called \"w3.org/.well-known/csvm\" at the url \"https://www.w3.org/.well-known/csvm\""
|
92
|
+
missing_files << "#{action_uri}.json"
|
93
|
+
missing_files << URI.join(action_uri, "csvm.json").to_s
|
94
|
+
else
|
95
|
+
missing_files << URI.join(action_uri, "/.well-known/csvm").to_s
|
96
|
+
end
|
97
|
+
missing_files << "#{action_uri}-metadata.json"
|
98
|
+
missing_files << URI.join(action_uri, "csv-metadata.json").to_s
|
99
|
+
end
|
100
|
+
entry["implicit"]&.each do |implicit|
|
101
|
+
implicit_uri, implicit_file = cache_file(implicit)
|
102
|
+
provided_files << implicit_uri.to_s
|
103
|
+
unless implicit_uri == metadata
|
104
|
+
file.puts "\t\tAnd I have a file called \"csvw/#{implicit}\" at the url \"#{implicit_uri}\""
|
105
|
+
end
|
106
|
+
end
|
107
|
+
missing_files.each do |uri|
|
108
|
+
file.puts "\t\tAnd there is no file at the url \"#{uri}\"" unless provided_files.include? uri
|
109
|
+
end
|
110
|
+
file.puts "\t\tWhen I carry out CSVW validation"
|
111
|
+
if entry["type"] == "csvt:WarningValidationTest"
|
112
|
+
file.puts "\t\tThen there should not be errors"
|
113
|
+
file.puts "\t\tAnd there should be warnings"
|
114
|
+
elsif entry["type"] == "csvt:NegativeValidationTest"
|
115
|
+
file.puts "\t\tThen there should be errors"
|
116
|
+
else
|
117
|
+
file.puts "\t\tThen there should not be errors"
|
118
|
+
file.puts "\t\tAnd there should not be warnings"
|
119
|
+
end
|
120
|
+
file.puts "\t"
|
121
|
+
end
|
122
|
+
end
|
123
|
+
end
|
data/features/support/webmock.rb
CHANGED
@@ -1,3 +1,3 @@
|
|
1
|
-
require
|
1
|
+
require "webmock/cucumber"
|
2
2
|
|
3
|
-
WebMock.disable_net_connect!(allow: %r{csvw/tests})
|
3
|
+
WebMock.disable_net_connect!(allow: %r{csvw/tests})
|
data/lib/csvlint/cli.rb
CHANGED
@@ -1,15 +1,13 @@
|
|
1
|
-
require
|
2
|
-
require
|
3
|
-
require
|
4
|
-
require
|
5
|
-
require
|
6
|
-
require 'thor'
|
1
|
+
require "csvlint"
|
2
|
+
require "rainbow"
|
3
|
+
require "active_support/json"
|
4
|
+
require "json"
|
5
|
+
require "thor"
|
7
6
|
|
8
|
-
require
|
7
|
+
require "active_support/inflector"
|
9
8
|
|
10
9
|
module Csvlint
|
11
10
|
class Cli < Thor
|
12
|
-
|
13
11
|
desc "myfile.csv OR csvlint http://example.com/myfile.csv", "Supports validating CSV files to check their syntax and contents"
|
14
12
|
|
15
13
|
option :dump_errors, desc: "Pretty print error and warning objects.", type: :boolean, aliases: :d
|
@@ -36,162 +34,167 @@ module Csvlint
|
|
36
34
|
|
37
35
|
private
|
38
36
|
|
39
|
-
|
40
|
-
|
41
|
-
|
42
|
-
|
43
|
-
|
44
|
-
|
37
|
+
def read_source(source)
|
38
|
+
if source.nil?
|
39
|
+
# If no source is present, try reading from stdin
|
40
|
+
if !$stdin.tty?
|
41
|
+
source = begin
|
42
|
+
StringIO.new($stdin.read)
|
43
|
+
rescue
|
44
|
+
nil
|
45
45
|
end
|
46
|
-
|
47
|
-
|
48
|
-
|
49
|
-
|
50
|
-
|
51
|
-
|
52
|
-
|
53
|
-
|
46
|
+
return_error "No CSV data to validate" if !options[:schema] && source.nil?
|
47
|
+
end
|
48
|
+
else
|
49
|
+
# If the source isn't a URL, it's a file
|
50
|
+
unless /^http(s)?/.match?(source)
|
51
|
+
begin
|
52
|
+
source = File.new(source)
|
53
|
+
rescue Errno::ENOENT
|
54
|
+
return_error "#{source} not found"
|
54
55
|
end
|
55
56
|
end
|
56
|
-
|
57
|
-
source
|
58
57
|
end
|
59
58
|
|
60
|
-
|
61
|
-
|
62
|
-
schema = Csvlint::Schema.load_from_uri(schema, false)
|
63
|
-
rescue Csvlint::Csvw::MetadataError => e
|
64
|
-
return_error "invalid metadata: #{e.message}#{" at " + e.path if e.path}"
|
65
|
-
rescue OpenURI::HTTPError, Errno::ENOENT
|
66
|
-
return_error "#{options[:schema]} not found"
|
67
|
-
end
|
59
|
+
source
|
60
|
+
end
|
68
61
|
|
69
|
-
|
70
|
-
|
71
|
-
|
62
|
+
def get_schema(schema)
|
63
|
+
begin
|
64
|
+
schema = Csvlint::Schema.load_from_uri(schema, false)
|
65
|
+
rescue Csvlint::Csvw::MetadataError => e
|
66
|
+
return_error "invalid metadata: #{e.message}#{" at " + e.path if e.path}"
|
67
|
+
rescue OpenURI::HTTPError, Errno::ENOENT
|
68
|
+
return_error "#{options[:schema]} not found"
|
69
|
+
end
|
72
70
|
|
73
|
-
|
71
|
+
if schema.instance_of?(Csvlint::Schema) && schema.description == "malformed"
|
72
|
+
return_error "invalid metadata: malformed JSON"
|
74
73
|
end
|
75
74
|
|
76
|
-
|
77
|
-
|
75
|
+
schema
|
76
|
+
end
|
78
77
|
|
79
|
-
|
80
|
-
|
81
|
-
|
82
|
-
|
78
|
+
def fetch_schema_tables(schema, options)
|
79
|
+
valid = true
|
80
|
+
|
81
|
+
unless schema.instance_of? Csvlint::Csvw::TableGroup
|
82
|
+
return_error "No CSV data to validate."
|
83
|
+
end
|
84
|
+
schema.tables.keys.each do |source|
|
85
|
+
unless /^http(s)?/.match?(source)
|
83
86
|
begin
|
84
|
-
source = source.sub("file:","")
|
85
|
-
source = File.new(
|
87
|
+
source = source.sub("file:", "")
|
88
|
+
source = File.new(source)
|
86
89
|
rescue Errno::ENOENT
|
87
90
|
return_error "#{source} not found"
|
88
|
-
end unless source =~ /^http(s)?/
|
89
|
-
valid &= validate_csv(source, schema, options[:dump_errors], nil, options[:werror])
|
90
|
-
end
|
91
|
-
|
92
|
-
exit 1 unless valid
|
93
|
-
end
|
94
|
-
|
95
|
-
def print_error(index, error, dump, color)
|
96
|
-
location = ""
|
97
|
-
location += error.row.to_s if error.row
|
98
|
-
location += "#{error.row ? "," : ""}#{error.column.to_s}" if error.column
|
99
|
-
if error.row || error.column
|
100
|
-
location = "#{error.row ? "Row" : "Column"}: #{location}"
|
101
|
-
end
|
102
|
-
output_string = "#{index+1}. "
|
103
|
-
if error.column && @schema && @schema.class == Csvlint::Schema
|
104
|
-
if @schema.fields[error.column - 1] != nil
|
105
|
-
output_string += "#{@schema.fields[error.column - 1].name}: "
|
106
91
|
end
|
107
92
|
end
|
108
|
-
|
109
|
-
|
110
|
-
output_string += ". #{error.content}" if error.content
|
93
|
+
valid &= validate_csv(source, schema, options[:dump_errors], nil, options[:werror])
|
94
|
+
end
|
111
95
|
|
112
|
-
|
96
|
+
exit 1 unless valid
|
97
|
+
end
|
113
98
|
|
114
|
-
|
115
|
-
|
99
|
+
def print_error(index, error, dump, color)
|
100
|
+
location = ""
|
101
|
+
location += error.row.to_s if error.row
|
102
|
+
location += "#{error.row ? "," : ""}#{error.column}" if error.column
|
103
|
+
if error.row || error.column
|
104
|
+
location = "#{error.row ? "Row" : "Column"}: #{location}"
|
105
|
+
end
|
106
|
+
output_string = "#{index + 1}. "
|
107
|
+
if error.column && @schema && @schema.instance_of?(Csvlint::Schema)
|
108
|
+
if @schema.fields[error.column - 1] != nil
|
109
|
+
output_string += "#{@schema.fields[error.column - 1].name}: "
|
116
110
|
end
|
117
111
|
end
|
112
|
+
output_string += error.type.to_s
|
113
|
+
output_string += ". #{location}" unless location.empty?
|
114
|
+
output_string += ". #{error.content}" if error.content
|
118
115
|
|
119
|
-
|
120
|
-
|
121
|
-
|
122
|
-
|
116
|
+
puts Rainbow(output_string).color(color)
|
117
|
+
|
118
|
+
if dump
|
119
|
+
pp error
|
123
120
|
end
|
121
|
+
end
|
124
122
|
|
125
|
-
|
126
|
-
|
127
|
-
|
123
|
+
def print_errors(errors, dump)
|
124
|
+
if errors.size > 0
|
125
|
+
errors.each_with_index { |error, i| print_error(i, error, dump, :red) }
|
128
126
|
end
|
127
|
+
end
|
129
128
|
|
130
|
-
|
131
|
-
|
129
|
+
def return_error(message)
|
130
|
+
puts Rainbow(message).red
|
131
|
+
exit 1
|
132
|
+
end
|
132
133
|
|
133
|
-
|
134
|
-
|
135
|
-
else
|
136
|
-
validator = Csvlint::Validator.new( source, {}, schema, { lambda: report_lines } )
|
137
|
-
end
|
134
|
+
def validate_csv(source, schema, dump, json, werror)
|
135
|
+
@error_count = 0
|
138
136
|
|
139
|
-
|
140
|
-
|
141
|
-
|
142
|
-
|
143
|
-
|
144
|
-
csv = "CSV"
|
145
|
-
end
|
137
|
+
validator = if json === true
|
138
|
+
Csvlint::Validator.new(source, {}, schema)
|
139
|
+
else
|
140
|
+
Csvlint::Validator.new(source, {}, schema, {lambda: report_lines})
|
141
|
+
end
|
146
142
|
|
147
|
-
|
148
|
-
|
149
|
-
|
150
|
-
|
151
|
-
|
152
|
-
|
153
|
-
|
154
|
-
}
|
155
|
-
}.to_json
|
156
|
-
print json
|
157
|
-
else
|
158
|
-
puts "\r\n#{csv} is #{validator.valid? ? Rainbow("VALID").green : Rainbow("INVALID").red}"
|
159
|
-
print_errors(validator.errors, dump)
|
160
|
-
print_errors(validator.warnings, dump)
|
161
|
-
end
|
143
|
+
csv = if source.instance_of?(String)
|
144
|
+
source
|
145
|
+
elsif source.instance_of?(File)
|
146
|
+
source.path
|
147
|
+
else
|
148
|
+
"CSV"
|
149
|
+
end
|
162
150
|
|
163
|
-
|
164
|
-
|
151
|
+
if json === true
|
152
|
+
json = {
|
153
|
+
validation: {
|
154
|
+
state: validator.valid? ? "valid" : "invalid",
|
155
|
+
errors: validator.errors.map { |v| hashify(v) },
|
156
|
+
warnings: validator.warnings.map { |v| hashify(v) },
|
157
|
+
info: validator.info_messages.map { |v| hashify(v) }
|
158
|
+
}
|
159
|
+
}.to_json
|
160
|
+
print json
|
161
|
+
else
|
162
|
+
puts "\r\n#{csv} is #{validator.valid? ? Rainbow("VALID").green : Rainbow("INVALID").red}"
|
163
|
+
print_errors(validator.errors, dump)
|
164
|
+
print_errors(validator.warnings, dump)
|
165
165
|
end
|
166
166
|
|
167
|
-
|
168
|
-
|
169
|
-
|
170
|
-
category: error.category,
|
171
|
-
row: error.row,
|
172
|
-
col: error.column
|
173
|
-
}
|
174
|
-
|
175
|
-
if error.column && @schema && @schema.class == Csvlint::Schema && @schema.fields[error.column - 1] != nil
|
176
|
-
field = @schema.fields[error.column - 1]
|
177
|
-
h[:header] = field.name
|
178
|
-
h[:constraints] = Hash[field.constraints.map {|k,v| [k.underscore, v] }]
|
179
|
-
end
|
167
|
+
return false if werror && validator.warnings.size > 0
|
168
|
+
validator.valid?
|
169
|
+
end
|
180
170
|
|
181
|
-
|
171
|
+
def hashify(error)
|
172
|
+
h = {
|
173
|
+
type: error.type,
|
174
|
+
category: error.category,
|
175
|
+
row: error.row,
|
176
|
+
col: error.column
|
177
|
+
}
|
178
|
+
|
179
|
+
if error.column && @schema && @schema.instance_of?(Csvlint::Schema) && @schema.fields[error.column - 1] != nil
|
180
|
+
field = @schema.fields[error.column - 1]
|
181
|
+
h[:header] = field.name
|
182
|
+
h[:constraints] = field.constraints.map { |k, v| [k.underscore, v] }.to_h
|
182
183
|
end
|
183
184
|
|
184
|
-
|
185
|
-
|
186
|
-
|
187
|
-
|
188
|
-
|
189
|
-
|
190
|
-
|
191
|
-
|
192
|
-
|
185
|
+
h
|
186
|
+
end
|
187
|
+
|
188
|
+
def report_lines
|
189
|
+
lambda do |row|
|
190
|
+
new_errors = row.errors.count
|
191
|
+
if new_errors > @error_count
|
192
|
+
print Rainbow("!").red
|
193
|
+
else
|
194
|
+
print Rainbow(".").green
|
193
195
|
end
|
196
|
+
@error_count = new_errors
|
194
197
|
end
|
195
|
-
|
198
|
+
end
|
196
199
|
end
|
197
200
|
end
|