From 3705e5e45986d66c5bb644f22b17de8e341839c9 Mon Sep 17 00:00:00 2001
From: Jonas Jenwald <jonas.jenwald@gmail.com>
Date: Fri, 24 Mar 2017 17:24:30 +0100
Subject: [PATCH] Use a proper `MessageHandler` for
 `PartialEvaluator.getTextContent` to avoid errors for fonts relying on
 built-in CMap files (PR 8064 follow-up)

*My apologies for inadvertently breaking this in PR 8064; apparently we don't have any tests that cover this use-case :(*

Without this patch `getTextContent` will fail if called before `getOperatorList`, since loading of fonts during text-extraction may require fetching of built-in CMap files.

*Please note:* The `text` test added here, which uses an already existing PDF file, fails without this patch.
---
 src/core/document.js    | 7 +------
 src/core/worker.js      | 2 +-
 test/test_manifest.json | 9 ++++++++-
 3 files changed, 10 insertions(+), 8 deletions(-)

diff --git a/src/core/document.js b/src/core/document.js
index 716b9a21d..0cb7dfe0e 100644
--- a/src/core/document.js
+++ b/src/core/document.js
@@ -310,14 +310,9 @@ var Page = (function PageClosure() {
       });
     },
 
-    extractTextContent: function Page_extractTextContent(task,
+    extractTextContent: function Page_extractTextContent(handler, task,
                                                          normalizeWhitespace,
                                                          combineTextItems) {
-      var handler = {
-        on: function nullHandlerOn() {},
-        send: function nullHandlerSend() {}
-      };
-
       var self = this;
 
       var pdfManager = this.pdfManager;
diff --git a/src/core/worker.js b/src/core/worker.js
index 756c9e8a6..ec8aa4b1c 100644
--- a/src/core/worker.js
+++ b/src/core/worker.js
@@ -906,7 +906,7 @@ var WorkerMessageHandler = {
         startWorkerTask(task);
         var pageNum = pageIndex + 1;
         var start = Date.now();
-        return page.extractTextContent(task, normalizeWhitespace,
+        return page.extractTextContent(handler, task, normalizeWhitespace,
                                        combineTextItems).then(
             function(textContent) {
           finishWorkerTask(task);
diff --git a/test/test_manifest.json b/test/test_manifest.json
index a266aea45..e99a638f6 100644
--- a/test/test_manifest.json
+++ b/test/test_manifest.json
@@ -2757,10 +2757,17 @@
       "md5": "797093d67c4d4d4231ac6e1fb66bf6c3",
       "rounds": 1,
       "link": true,
-      "firstPage": 1,
       "lastPage": 1,
       "type": "eq"
     },
+    {  "id": "mao-text",
+       "file": "pdfs/mao.pdf",
+       "md5": "797093d67c4d4d4231ac6e1fb66bf6c3",
+       "rounds": 1,
+       "link": true,
+       "lastPage": 1,
+       "type": "text"
+    },
     {  "id": "noembed-identity",
       "file": "pdfs/noembed-identity.pdf",
       "md5": "05d3803b6c22451e18cb60d8d8c75c0c",