pdf-reader-find_text 0.1.1 → 1.0.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 19766f6210ef79a6a29a22f6c0f501c8acc2cb18d539511a8fd163962735264f
-  data.tar.gz: 101ced07a4294793b2f7b8addb54e7df2f25a254fc5c88e0c5f6f2c13dba6453
+  metadata.gz: 3ca302a11748be3c14295a72be6e3e231f1bce93cf92b4eb9a0cec8ff022c1f9
+  data.tar.gz: 79bea9f5a62553f91106ad7d47a93d56fd602b86729a911eaf06ec88c39817dc
 SHA512:
-  metadata.gz: 27d305f423497fbf1bdb14be0eb777250bd36e6b16f673609e3d193fd9ca317eb7e03b8669448c8987c39bfd15ccabeedc8f823fad654567da08b960d5e0a787
-  data.tar.gz: 4ac4586a856edc0202b6ce60819de435b4786c369a1ab3e022ccf5907188184b7d2b89b19fd027a6bc8495e81ea0aa41f6761c5881531bf778ebf0710bf3d0a1
+  metadata.gz: fab73686e49d78ae4eaceb14cbb84926093c2c54eb088e072b6bab66794d0c5d1a5042bac82d2cf30f1254cb27d740d846685db54dc3b8d578e5ddb0b325cd3d
+  data.tar.gz: e89dc5f098da69fec703ccc9b6d2aae92c5ff25d2b29b6ef90bd3081e8303626aad9e05db5f535a4f2c77fd4158ac214048ba51e82d8d6d594f29e6b70f2d121

data/CHANGELOG.md

@@ -1,5 +1,13 @@
 ## [Unreleased]
 
+## [0.1.2] - 2022-02-24
+
+- Handle strings with spaces in a better way
+
+## [0.1.1] - 2022-02-23
+
+- Remove spaces before looking for text
+
 ## [0.1.0] - 2022-02-23
 
 - Initial release

data/lib/pdf/reader/find_text/version.rb

@@ -3,7 +3,7 @@
 module PDF
   class Reader
     module FindText
-      VERSION = "0.1.1"
+      VERSION = "1.0.0"
     end
   end
 end

data/lib/pdf/reader/find_text.rb

@@ -5,14 +5,22 @@ require "pdf-reader"
 require_relative "find_text/version"
 
 module PDF::Reader::FindText
-  def find_text(text)
-    text = text.tr(' ', '')
+  def find_text(value)
+    runs(merge: false).each_cons(value.tr(' ', '').size).map do |chars|
+      string = merge_runs_with_max_length(chars, value.size)
+      string if string.text[0, value.size] == value
+    end.compact
+  end
+
+  private
 
-    runs(merge: false).each_cons(text.size).select do |r|
-      r.map(&:text).join == text
-    end.map do |r|
-      PDF::Reader::TextRun.new r.first.x, r.first.y,
-        r.sum(&:width), r.map(&:font_size).max, r.map(&:text).join
+  def merge_runs_with_max_length(chars, length)
+    chars.inject do |string, char|
+      if string.mergable?(char) && string.text.size < length
+        string + char
+      else
+        string
+      end
     end
   end
 end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: pdf-reader-find_text
 version: !ruby/object:Gem::Version
-  version: 0.1.1
+  version: 1.0.0
 platform: ruby
 authors:
 - Guillaume Dott
 autorequire:
 bindir: exe
 cert_chain: []
-date: 2022-02-23 00:00:00.000000000 Z
+date: 2022-11-25 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: pdf-reader
@@ -16,14 +16,14 @@ dependencies:
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: 2.9.2
+        version: '2.9'
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: 2.9.2
+        version: '2.9'
 description: PDF::Reader extension to find text in PDF and get the page and position
 email:
 - guillaume+github@dott.fr
@@ -61,7 +61,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
-rubygems_version: 3.3.5
+rubygems_version: 3.3.25
 signing_key:
 specification_version: 4
 summary: PDF::Reader extension to find text in PDF