string_splitter 0.1.0 → 0.2.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 3e22243b9c975e4ac2ffa8f03871f5c41fd406cb3b4b780dd303e89bcf024c45
-  data.tar.gz: fced8a0defba0a46d1dde5ffef3c7ff9a93c4f43afa8d0b19c98d93524c466f4
+  metadata.gz: fcb033c8d7804dab11a7756f3fafb06292650c048947d09b01d479e354d2dfa4
+  data.tar.gz: ffc6e4fae751883e2f7731232ccb3b539eb95ff030d716360b284e21339651ad
 SHA512:
-  metadata.gz: 2d7991eb02cea9c35a26e9248c33ff923b71637b476110f58d4b35abae398efa5603eca6d0ed178d797a69d79f6b1caa1468ec4753e185d60280ccfe4049bc1a
-  data.tar.gz: a944e39f2105d61585ca703073dcedd3e4b4e2be9dd88db01bfef07ab67bb265b15741d3b8a558c505525e06f800385f857a81945f527256102fdcef3084ee89
+  metadata.gz: b6ccb81fd4b270251f0f1dc4108e67485a9795a3fd8bdb3ce852a5d7498933e0f431da0d60732fc61e9224c4676ee5104858db0e40ed6589e03eb9fa147fc0dc
+  data.tar.gz: f4d011a2fc127645ca5bbf9fbb607d854e021021b69047a7fbdc6ba9124edbdca750901147a0cce22cd80ca05197355de94c9e3bd353b1a1a1ebfde136eefdce

data/CHANGELOG.md

@@ -1,7 +1,12 @@
+## 0.2.0 - 2018-06-22
+
+- **breaking change**: make `index` (AKA `offset`) 0-based and add `position` (AKA `pos`)
+  as the 1-based accessor
+
 ## 0.1.0 - 2018-06-22
 
-- **breaking change**: the block now takes a single `split` object with an `index`
-  field, rather than seperate `index` and `split` arguments
+- **breaking change**: the block now takes a single `split` object with an
+  `index` accessor, rather than seperate `index` and `split` arguments
 - add support for negative indices in the value supplied to the `at` option
 - add a `count` field to the split object containing the total number of splits
 

data/README.md

@@ -51,17 +51,17 @@ ss.split("foo:bar:baz:quux", ":", at: 1)
 ss.split("foo:bar:baz:quux", ":", at: -1)
 # => ["foo:bar:baz", "quux"]
 
-# split on multiple separator indices
-ss.split("1:2:3:4:5:6:7:8:9", ":", at: [1..3, -1])
-# => ["1", "2", "3", "4:5:6:7:8", "9"]
+# split at multiple separator positions
+ss.split("1:2:3:4:5:6:7:8:9", ":", at: [1..3, -2])
+# => ["1", "2", "3", "4:5:6:7", "8:9"]
 
 # split from the right
 ss.rsplit("1:2:3:4:5:6:7:8:9", ":", at: [1..3, 5])
 # => ["1:2:3:4", "5:6", "7", "8", "9"]
 
 # full control via a block
-result = s.split('a:a:a:b:c:c:e:a:a:d:c', ":") do |split|
-  split.index > 1 && split.lhs == split.rhs
+result = ss.split('a:a:a:b:c:c:e:a:a:d:c', ":") do |split|
+  split.index > 0 && split.lhs == split.rhs
 end
 # => ["a:a", "a:b:c", "c:e:a", "a:d:c"]
 ```
@@ -79,8 +79,9 @@ and handle a few common cases e.g.:
 But, because the API is squeezed into two overloaded parameters (the separator and the limit),
 achieving the desired effects can be tricky. For instance, while `String#split` removes empty
 trailing fields (by default), it provides no way to remove *all* empty fields. Likewise, the
-cramped API means there's no way to combine e.g. a limit (positive integer) with the option
-to preserve empty fields (negative integer).
+cramped API means there's no way to e.g. combine a limit (positive integer) with the option
+to preserve empty fields (negative integer), or use backreferences in a separator pattern
+without including its captured subexpressions in the result.
 
 If `split` was being written from scratch, without the baggage of its legacy API,
 it's possible that some of these options would be made explicit rather than overloading
@@ -98,14 +99,14 @@ and delegating the strategy — i.e. which splits should be accepted or rejected
 ```ruby
 ss = StringSplitter.new
 
-ss.split("foo:bar:baz", ":") { |split| split.index == 1 }
+ss.split("foo:bar:baz", ":") { |split| split.index == 0 }
 # => ["foo", "bar:baz"]
 
-ss.split("foo:bar:baz", ":") { |split| split.index == split.count }
+ss.split("foo:bar:baz", ":") { |split| split.position == split.count }
 # => ["foo:bar", "baz"]
 ```
 
-As a shortcut, the common case of splitting on separators at one or more indices is supported by an option:
+As a shortcut, the common case of splitting on separators at one or more positions is supported by an option:
 
 ```ruby
 ss.split('foo:bar:baz:quux', ':', at: [1, -1]) # => ["foo", "bar:baz", "quux"]
@@ -119,7 +120,7 @@ As an example, the nominally unstructured output of many Unix commands is often,
 that's tantalizingly close to being machine-readable, apart from a few pesky exceptions e.g.:
 
 ```bash
-$ ls -la
+$ ls -l
 
 -rw-r--r-- 1 user users   87 Jun 18 18:16 CHANGELOG.md
 -rw-r--r-- 1 user users  254 Jun 19 21:21 Gemfile
@@ -151,7 +152,7 @@ instead of:
 One way to work around this is to parse the whole line e.g.:
 
 ```ruby
-line.match(/^(\S+) \s+ (\d+) \s+ (\S+) \s+ (\S+) \s+ (\d+) \s+ (\S+ \s+ \d+ \s+ \S+) (.+)$/x)
+line.match(/^(\S+) \s+ (\d+) \s+ (\S+) \s+ (\S+) \s+ (\d+) \s+ (\S+ \s+ \d+ \s+ \S+) \s+ (.+)$/x)
 ```
 
 But that requires us to specify *everything*. What we really want is a version of `split`
@@ -164,7 +165,7 @@ this easy to handle, either via a block:
 
 ```ruby
 ss.split(line) do |split|
-  case split.index when 1..5, 8 then true end
+  case split.position when 1..5, 8 then true end
 end
 # => ["-rw-r--r--", "1", "user", "users", "87", "Jun 18 18:16", "CHANGELOG.md"]
 ```
@@ -178,7 +179,7 @@ ss.split(line, at: [1..5, 8])
 
 # VERSION
 
-0.1.0
+0.2.0
 
 # SEE ALSO
 

data/lib/string_splitter.rb

@@ -16,7 +16,14 @@ class StringSplitter
   DEFAULT_SEPARATOR = /\s+/
   NO_SPLITS = []
 
-  Split = Value.new(:captures, :count, :index, :lhs, :rhs, :separator)
+  Split = Value.new(:captures, :count, :index, :lhs, :rhs, :separator) do
+    def position
+      index + 1
+    end
+
+    alias_method :offset, :index
+    alias_method :pos, :position
+  end
 
   def initialize(
     default_separator: DEFAULT_SEPARATOR,
@@ -126,7 +133,7 @@ class StringSplitter
   def split_common(string, delimiter, at, block)
     unless (match = string.match(delimiter))
       result = (@remove_empty && string.empty?) ? [] : [string]
-      return [result, block, NO_SPLITS, 0, 0]
+      return [result, block, NO_SPLITS, 0, -1]
     end
 
     ncaptures = match.captures.length
@@ -185,13 +192,13 @@ class StringSplitter
         end
 
         block = lambda do |split|
-          case split.index when *at then true else false end
+          case split.position when *at then true else false end
         end
       else
         block = ACCEPT
       end
     end
 
-    [result, block, splits, count, 0]
+    [result, block, splits, count, -1]
   end
 end

data/lib/string_splitter/version.rb

@@ -1,5 +1,5 @@
 # frozen_string_literal: true
 
 class StringSplitter
-  VERSION = '0.1.0'
+  VERSION = '0.2.0'
 end

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: string_splitter
 version: !ruby/object:Gem::Version
-  version: 0.1.0
+  version: 0.2.0
 platform: ruby
 authors:
 - chocolateboy