From 85c52f1fd67f540b5defa671fb324de0b175c868 Mon Sep 17 00:00:00 2001
From: Chas Emerick <chas@cemerick.com>
Date: Thu, 13 Oct 2016 07:47:17 -0400
Subject: [PATCH] Fix getTextContent evaluation to only apply TJ horizontal
 offsets using numeric items/args

While the array argument to TJ should only contain strings and numbers, other
unfortunate items are found in PDFs in the wild, e.g.:

[(Grandes) 0.0 Tc
-250.0 (Client\350les,) 0.0 Tc
-250.0 (Financements) 0.0 Tc
-250.0 (et) 0.0 Tc
-250.0 (March\351s) ] TJ

getOperatorList already properly ignores any non-string, non-numeric values in
TJ arrays; without this patch to getTextContent, returned text items can have
NaN widths due to calculations being applied to those non-numeric values.
---
 src/core/evaluator.js              |  2 +-
 test/pdfs/.gitignore               |  1 +
 test/pdfs/operator-in-TJ-array.pdf | 70 ++++++++++++++++++++++++++++++
 test/test_manifest.json            |  7 +++
 4 files changed, 79 insertions(+), 1 deletion(-)
 create mode 100644 test/pdfs/operator-in-TJ-array.pdf

diff --git a/src/core/evaluator.js b/src/core/evaluator.js
index 5a0450efe..3f05f820b 100644
--- a/src/core/evaluator.js
+++ b/src/core/evaluator.js
@@ -1531,7 +1531,7 @@ var PartialEvaluator = (function PartialEvaluatorClosure() {
               for (var j = 0, jj = items.length; j < jj; j++) {
                 if (typeof items[j] === 'string') {
                   buildTextContentItem(items[j]);
-                } else {
+                } else if (isNum(items[j])) {
                   ensureTextContentItem();
 
                   // PDF Specification 5.3.2 states:
diff --git a/test/pdfs/.gitignore b/test/pdfs/.gitignore
index 173e86f1f..792230050 100644
--- a/test/pdfs/.gitignore
+++ b/test/pdfs/.gitignore
@@ -258,3 +258,4 @@
 !annotation-text-widget.pdf
 !annotation-choice-widget.pdf
 !zero_descent.pdf
+!operator-in-TJ-array.pdf
diff --git a/test/pdfs/operator-in-TJ-array.pdf b/test/pdfs/operator-in-TJ-array.pdf
new file mode 100644
index 000000000..09b2655d8
--- /dev/null
+++ b/test/pdfs/operator-in-TJ-array.pdf
@@ -0,0 +1,70 @@
+%PDF-1.3
+1 0 obj
+<</Kids  [8 0 R]
+  /Type  /Pages
+  /Count 1>>
+endobj
+2 0 obj
+<</Type  /Catalog
+  /Pages 1 0 R>>
+endobj
+3 0 obj
+<</ProcSet [/PDF /ImageC /Text]
+  /Font    <</F7 10 0 R>>>>
+endobj
+4 0 obj
+<</Type     /Info
+  /Producer (null)>>
+endobj
+5 0 obj
+<< >>
+stream
+BT
+/F7 10 Tf
+0 g
+0.0 Tc
+1 0 0 1 22.677 732.083 Tm [(Grandes) 0.0 Tc
+-250.0 (Client\350les,) 0.0 Tc
+-250.0 (Financements) 0.0 Tc
+-250.0 (et) 0.0 Tc
+-250.0 (March\351s) ] TJ
+0.0 Tc
+ET
+
+endstream
+endobj
+8 0 obj
+<</Contents  5 0 R
+  /Type      /Page
+  /Resources 3 0 R
+  /Parent    1 0 R
+  /MediaBox  [0 0 595 839]>>
+endobj
+10 0 obj
+<</Name     /F7
+  /Subtype  /Type1
+  /Type     /Font
+  /BaseFont /Times-Bold
+  /Encoding /WinAnsiEncoding>>
+xref
+0 11
+0000000000 65535 f 
+0000000009 00000 n 
+0000000070 00000 n 
+0000000120 00000 n 
+0000000195 00000 n 
+0000000249 00000 n 
+0000000000 65535 f 
+0000000000 65535 f 
+0000000470 00000 n 
+0000000000 65535 f 
+0000000590 00000 n 
+trailer
+<<
+/Size 13
+/Root 2 0 R
+/Info 4 0 R
+>>
+startxref
+707
+%%EOF
diff --git a/test/test_manifest.json b/test/test_manifest.json
index 231921876..8b4a6064a 100644
--- a/test/test_manifest.json
+++ b/test/test_manifest.json
@@ -3267,5 +3267,12 @@
        "rounds": 1,
        "lastPage": 1,
        "type": "text"
+    },
+    {  "id": "operator-in-TJ-array",
+       "file": "pdfs/operator-in-TJ-array.pdf",
+       "md5": "dfe0f15a45be18eca142adaf760984ee",
+       "link": false,
+       "rounds": 1,
+       "type": "text"
     }
 ]