From 355813462f1cf6c76f246034ed33e3148816e5e6 Mon Sep 17 00:00:00 2001
From: Guillaume Dott <guillaume+github@dott.fr>
Date: Thu, 24 Feb 2022 10:00:10 +0100
Subject: [PATCH] Handle strings with spaces

---
 lib/pdf/reader/find_text.rb | 22 +++++++++++++++-------
 1 file changed, 15 insertions(+), 7 deletions(-)

diff --git a/lib/pdf/reader/find_text.rb b/lib/pdf/reader/find_text.rb
index ea928f9..1876f2b 100644
--- a/lib/pdf/reader/find_text.rb
+++ b/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
 
-    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
+  private
+
+  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