remote_table 3.0.0 → 3.1.0

checksums.yaml

@@ -1,15 +1,15 @@
 ---
 !binary "U0hBMQ==":
   metadata.gz: !binary |-
-    NmMzNjkxNDIyZmJlOGQ0MjNlNjZhZjIwMTE1NDNkNWMzN2I2ZGYxNg==
+    YzE1ZTc4ZmI1MGYzMWNmNmI3MTJjNmU5ZWE2NmEyZmMzNGY0MDAyOA==
   data.tar.gz: !binary |-
-    ZWQ4MDg4YzQwNTEwMTlkMjk3OTM1NzQzOTI5YzNhODBiOWU3NDVmMA==
+    MWExYTNiZjk0ZGE2MmEzNWRjYjI4YWEyMzVkMzU5MWE1YTAwYmJhOA==
 SHA512:
   metadata.gz: !binary |-
-    YTg0N2ZiZjBhNTllNTg2MmEzMDQ0OGZkZDQwODNkMDg3YjUzY2M1YWMwZTdj
-    ODcwMWZhNzQxMzI0ZDY5MDU2MTY5ZDVkNjEwMzZkY2Q3YzExMmFmMzUwNzcz
-    MzI3ZjY1N2M2ZTYzYjY4YmNhN2RlODQzZTIwMDkyYmEyM2Q1Zjk=
+    ZWVhNzUxMWRmZWE5Yjk5YmMxZmZiZmUyNWUxYjE2NzNjYjBlYjE4ZDc2Y2Jj
+    NGY0ZDY1MGVmZDk1MDY0NDRiNTNmYTc3ZDViOGE3YjZmZTAxMjk2N2Y2M2Nl
+    NzA1N2M2ZmE0OWY2MGMyNjYyNTlmOWRmMjRlODJmNGQ3MmUyNmM=
   data.tar.gz: !binary |-
-    MWY4YjMyNjA3Yzc1ZTRiMDYxNTEyMjk4M2Q5YmFhZDc2OTUwNTBiODVhZWVi
-    YTIwNTEzYmRmMjdiMGRjODkzNTIyM2FlM2FkMWNhNDhjNDk3YWQ4NTk3YzJl
-    OWVlMjkwY2UyMTZiNzk0MjM0Mjg3ZTFhNTcwYWZiNjVhNDMyMzM=
+    NmIwNGI4ZjEzNDIyOTE4ZjA3ZmFlZjJiOTY2OTk5ZDRmZWEyMjdjNWZkODc0
+    NzBlMWVlMWEzMWE2NGU0YTcyMjRjOWIwMGNlZDAyNDI4MGZkNmJkNWQ4NTlj
+    MzM0ZWFlZTMwNDM5ZGJjYWNlZDMxN2NhYmM5ZTgyMTFlMjk3NjQ=

data/CHANGELOG

@@ -1,3 +1,13 @@
+3.1.0 / 2014-01-06
+
+* Breaking changes
+
+  * Stop requiring rubyzip2 on behalf of Roo per @rossmeissl https://github.com/seamusabshere/remote_table/issues/15 ... you may have to require it yourself
+
+* Enhancements
+
+  * by default, treat single and double quotes as "not special" in pipe- or tab-delimited files - thanks @dwillis https://github.com/seamusabshere/remote_table/pull/14
+
 3.0.0 / 2013-11-26
 
 * Breaking changes

data/lib/remote_table.rb

@@ -156,8 +156,6 @@ class RemoteTable
     :keep_blank_rows => false,
     :skip => 0,
     :encoding => 'UTF-8',
-    :delimiter => ',',
-    :quote_char => '"',
   }
   OLD_SETTING_NAMES = {
     :pre_select => [:select],

data/lib/remote_table/delimited.rb

@@ -63,11 +63,24 @@ class RemoteTable
     end
 
     def csv_options
-      {
+      retval = {
         skip_blanks: !keep_blank_rows,
-        col_sep:     delimiter,
-        quote_char:  quote_char,
       }
+      if delimiter
+        retval[:col_sep] = delimiter
+      end
+      if adaptive_quote_char
+        retval[:quote_char] = adaptive_quote_char
+      end
+      retval
+    end
+
+    def adaptive_quote_char
+      if quote_char
+        quote_char
+      elsif delimiter == "\t" or delimiter == '|'
+        "\0"
+      end
     end
 
     def headers

data/lib/remote_table/plaintext.rb

@@ -28,7 +28,7 @@ class RemoteTable
       harmful = [ Plaintext.soft_hyphen(encoding), UTF8_BOM ]
       local_copy.in_place :perl, "s/#{harmful.join('//g; s/')}//g"
     end
-    
+
     # No matter what the file encoding is SUPPOSED to be, run it through the system iconv binary to make sure it's UTF-8
     #
     # @example

data/lib/remote_table/version.rb

@@ -1,3 +1,3 @@
 class RemoteTable
-  VERSION = '3.0.0'
+  VERSION = '3.1.0'
 end

data/remote_table.gemspec

@@ -7,8 +7,8 @@ Gem::Specification.new do |s|
   s.authors     = ["Seamus Abshere", "Andy Rossmeissl"]
   s.email       = ["seamus@abshere.net"]
   s.homepage    = "https://github.com/seamusabshere/remote_table"
-  s.summary     = %{Open Google Docs spreadsheets, local or remote XLSX, XLS, ODS, CSV (comma separated), TSV (tab separated), other delimited, fixed-width files, and shapefiles.}
-  s.description = %{Open Google Docs spreadsheets, local or remote XLSX, XLS, ODS, CSV (comma separated), TSV (tab separated), other delimited, fixed-width files, and shapefiles. Returns an Array of Arrays or Hashes, depending on whether there are headers.}
+  s.summary     = %{Open local or remote XLSX, XLS, ODS, CSV (comma separated), TSV (tab separated), other delimited, fixed-width files, and Google Docs. Returns an enumerator of Arrays or Hashes, depending on whether there are headers.}
+  s.description = %{Open local or remote XLSX, XLS, ODS, CSV (comma separated), TSV (tab separated), other delimited, fixed-width files, and Google Docs. Returns an enumerator of Arrays or Hashes, depending on whether there are headers.}
 
   s.rubyforge_project = "remotetable"
 
@@ -24,7 +24,6 @@ Gem::Specification.new do |s|
   s.add_runtime_dependency 'unix_utils', '>=0.0.8'
   s.add_runtime_dependency 'fastercsv', '>=1.5.0'
   s.add_runtime_dependency 'hash_digest'
-  s.add_runtime_dependency 'rubyzip2'
 
   s.add_development_dependency 'errata', '>=0.2.0'
   s.add_development_dependency 'minitest'

data/test/data/cm.pathological.txt

@@ -0,0 +1,7 @@
+C00008896|`OPEIU LOCAL 153 '"|VOTE|"' (VOICE OF THE ELECTORATE) COMMITTEE`|RICHARD J LANIGAN|265 WEST 14TH ST.||NEW YORK|NY|10011|U|Q||Q|L|EMPLOYEES INT'L UNION; OFFICE & PROF.|
+C00009282|NORFOLK SOUTHERN CORPORATION GOOD GOVERNMENT FUND|LEDOUX, MARQUE|ONE CONSTITUTION AVE NE||WASHINGTON|DC|20002|B|Q|UNK|M|C|NORFOLK SOUTHERN CORPORATION|
+C00009357|THE RECORDING INDUSTRY ASSOCIATION OF AMERICA POLITICAL ACTION COMMITTEE|GLAZIER, MITCH|1025 F STREET NW|10TH FLOOR|WASHINGTON|DC|20004|B|Q||Q|T|THE RECORDING INDUSTRY ASSOCIATION OF AMERICA, INC.|
+C00009423|LAND O'LAKES, INC., PAC|GRABOW, KAREN|P.O. BOX 64101||ST. PAUL|MN|55164|B|Q||Q|V|LAND O'LAKES, INC.|
+C00009456|3RD CONGRESSIONAL DISTRICT DEMOCRATIC PARTY OF WISCONSIN|UGLAND, GERALD DAVID MR.|2450 RIVER BEND ROAD||PLOVER|WI|544672728|U|Y|DEM|Q||DEMOCRATIC PARTY OF WISCONSIN|
+C00009597|NATIONAL COUNCIL OF COAL LESSORS INC PAC|CRAWFORD, THOMAS|101 CONSTITUTION AVENUE NW|SUITE 900|WASHINGTON|DC|20001|U|Q||A|T|COAL LESSORS INC; NAT'L COUNCIL OF|
+C00277525|`JERRY CARROLL |S| COMMITTEE`|JERRY CARROLL|PO BOX 9079||STOCKTON|CA|95208|P|S|IND|A|||S2CA00591

data/test/data/cm.tsv

@@ -0,0 +1,7 @@
+C00008896	OPEIU LOCAL 153 "VOTE" (VOICE OF THE ELECTORATE) COMMITTEE	RICHARD J LANIGAN	265 WEST 14TH ST.		NEW YORK	NY	10011	U	Q		Q	L	EMPLOYEES INT'L UNION; OFFICE & PROF.	
+C00009282	NORFOLK SOUTHERN CORPORATION GOOD GOVERNMENT FUND	LEDOUX, MARQUE	ONE CONSTITUTION AVE NE		WASHINGTON	DC	20002	B	Q	UNK	M	C	NORFOLK SOUTHERN CORPORATION	
+C00009357	THE RECORDING INDUSTRY ASSOCIATION OF AMERICA POLITICAL ACTION COMMITTEE	GLAZIER, MITCH	1025 F STREET NW	10TH FLOOR	WASHINGTON	DC	20004	B	Q		Q	T	THE RECORDING INDUSTRY ASSOCIATION OF AMERICA, INC.	
+C00009423	LAND O'LAKES, INC., PAC	GRABOW, KAREN	P.O. BOX 64101		ST. PAUL	MN	55164	B	Q		Q	V	LAND O'LAKES, INC.	
+C00009456	3RD CONGRESSIONAL DISTRICT DEMOCRATIC PARTY OF WISCONSIN	UGLAND, GERALD DAVID MR.	2450 RIVER BEND ROAD		PLOVER	WI	544672728	U	Y	DEM	Q		DEMOCRATIC PARTY OF WISCONSIN	
+C00009597	NATIONAL COUNCIL OF COAL LESSORS INC PAC	CRAWFORD, THOMAS	101 CONSTITUTION AVENUE NW	SUITE 900	WASHINGTON	DC	20001	U	Q		A	T	COAL LESSORS INC; NAT'L COUNCIL OF	
+C00277525	JERRY CARROLL "S" COMMITTEE	JERRY CARROLL	PO BOX 9079		STOCKTON	CA	95208	P	S	IND	A			S2CA00591

data/test/data/cm.txt

@@ -0,0 +1,7 @@
+C00008896|OPEIU LOCAL 153 "VOTE" (VOICE OF THE ELECTORATE) COMMITTEE|RICHARD J LANIGAN|265 WEST 14TH ST.||NEW YORK|NY|10011|U|Q||Q|L|EMPLOYEES INT'L UNION; OFFICE & PROF.|
+C00009282|NORFOLK SOUTHERN CORPORATION GOOD GOVERNMENT FUND|LEDOUX, MARQUE|ONE CONSTITUTION AVE NE||WASHINGTON|DC|20002|B|Q|UNK|M|C|NORFOLK SOUTHERN CORPORATION|
+C00009357|THE RECORDING INDUSTRY ASSOCIATION OF AMERICA POLITICAL ACTION COMMITTEE|GLAZIER, MITCH|1025 F STREET NW|10TH FLOOR|WASHINGTON|DC|20004|B|Q||Q|T|THE RECORDING INDUSTRY ASSOCIATION OF AMERICA, INC.|
+C00009423|LAND O'LAKES, INC., PAC|GRABOW, KAREN|P.O. BOX 64101||ST. PAUL|MN|55164|B|Q||Q|V|LAND O'LAKES, INC.|
+C00009456|3RD CONGRESSIONAL DISTRICT DEMOCRATIC PARTY OF WISCONSIN|UGLAND, GERALD DAVID MR.|2450 RIVER BEND ROAD||PLOVER|WI|544672728|U|Y|DEM|Q||DEMOCRATIC PARTY OF WISCONSIN|
+C00009597|NATIONAL COUNCIL OF COAL LESSORS INC PAC|CRAWFORD, THOMAS|101 CONSTITUTION AVENUE NW|SUITE 900|WASHINGTON|DC|20001|U|Q||A|T|COAL LESSORS INC; NAT'L COUNCIL OF|
+C00277525|JERRY CARROLL "S" COMMITTEE|JERRY CARROLL|PO BOX 9079||STOCKTON|CA|95208|P|S|IND|A|||S2CA00591

data/test/test_remote_table.rb

@@ -59,6 +59,22 @@ describe RemoteTable do
     f.close
   end
 
+  it "treats quotes as not special in a pipe-delimited file" do
+    t = RemoteTable.new "file://#{File.expand_path('../data/cm.txt', __FILE__)}", :delimiter => '|', :headers => false
+    t[0][1].must_equal %{OPEIU LOCAL 153 "VOTE" (VOICE OF THE ELECTORATE) COMMITTEE}
+  end
+
+  it "treats quotes as not special in a tab-delimited file" do
+    t = RemoteTable.new "file://#{File.expand_path('../data/cm.tsv', __FILE__)}", :delimiter => "\t", :headers => false
+    t[0][1].must_equal %{OPEIU LOCAL 153 "VOTE" (VOICE OF THE ELECTORATE) COMMITTEE}
+  end
+
+  # using backticks
+  it "allows quoted pipes in a pipe-delimited file" do
+    t = RemoteTable.new "file://#{File.expand_path('../data/cm.pathological.txt', __FILE__)}", :delimiter => '|', :headers => false, :quote_char => '`'
+    t[0][1].must_equal %{OPEIU LOCAL 153 '"|VOTE|"' (VOICE OF THE ELECTORATE) COMMITTEE}
+  end
+
   it "open a yaml" do
     t = RemoteTable.new "file://#{File.expand_path('../data/data.yml', __FILE__)}"
     t[0]['name'].must_equal 'Seamus Abshere'

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: remote_table
 version: !ruby/object:Gem::Version
-  version: 3.0.0
+  version: 3.1.0
 platform: ruby
 authors:
 - Seamus Abshere
@@ -9,7 +9,7 @@ authors:
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2013-11-26 00:00:00.000000000 Z
+date: 2014-01-06 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: activesupport
@@ -109,20 +109,6 @@ dependencies:
     - - ! '>='
       - !ruby/object:Gem::Version
         version: '0'
-- !ruby/object:Gem::Dependency
-  name: rubyzip2
-  requirement: !ruby/object:Gem::Requirement
-    requirements:
-    - - ! '>='
-      - !ruby/object:Gem::Version
-        version: '0'
-  type: :runtime
-  prerelease: false
-  version_requirements: !ruby/object:Gem::Requirement
-    requirements:
-    - - ! '>='
-      - !ruby/object:Gem::Version
-        version: '0'
 - !ruby/object:Gem::Dependency
   name: errata
   requirement: !ruby/object:Gem::Requirement
@@ -221,9 +207,9 @@ dependencies:
     - - ! '>='
       - !ruby/object:Gem::Version
         version: '0'
-description: Open Google Docs spreadsheets, local or remote XLSX, XLS, ODS, CSV (comma
-  separated), TSV (tab separated), other delimited, fixed-width files, and shapefiles.
-  Returns an Array of Arrays or Hashes, depending on whether there are headers.
+description: Open local or remote XLSX, XLS, ODS, CSV (comma separated), TSV (tab
+  separated), other delimited, fixed-width files, and Google Docs. Returns an enumerator
+  of Arrays or Hashes, depending on whether there are headers.
 email:
 - seamus@abshere.net
 executables: []
@@ -256,6 +242,9 @@ files:
 - test/data/airports.utf8.csv
 - test/data/backup/http___www.customerreferenceprogram.org_uploads_CRP_RFP_template.xlsx
 - test/data/bom.csv
+- test/data/cm.pathological.txt
+- test/data/cm.tsv
+- test/data/cm.txt
 - test/data/color.csv
 - test/data/data.yml
 - test/data/faa-aircraft.html.bz2
@@ -307,12 +296,16 @@ rubyforge_project: remotetable
 rubygems_version: 2.1.11
 signing_key: 
 specification_version: 4
-summary: Open Google Docs spreadsheets, local or remote XLSX, XLS, ODS, CSV (comma
-  separated), TSV (tab separated), other delimited, fixed-width files, and shapefiles.
+summary: Open local or remote XLSX, XLS, ODS, CSV (comma separated), TSV (tab separated),
+  other delimited, fixed-width files, and Google Docs. Returns an enumerator of Arrays
+  or Hashes, depending on whether there are headers.
 test_files:
 - test/data/airports.utf8.csv
 - test/data/backup/http___www.customerreferenceprogram.org_uploads_CRP_RFP_template.xlsx
 - test/data/bom.csv
+- test/data/cm.pathological.txt
+- test/data/cm.tsv
+- test/data/cm.txt
 - test/data/color.csv
 - test/data/data.yml
 - test/data/faa-aircraft.html.bz2