Return-Path: X-Original-To: apmail-pdfbox-commits-archive@www.apache.org Delivered-To: apmail-pdfbox-commits-archive@www.apache.org Received: from mail.apache.org (hermes.apache.org [140.211.11.3]) by minotaur.apache.org (Postfix) with SMTP id B0D9217CA7 for ; Sun, 23 Nov 2014 16:52:59 +0000 (UTC) Received: (qmail 19655 invoked by uid 500); 23 Nov 2014 16:52:59 -0000 Delivered-To: apmail-pdfbox-commits-archive@pdfbox.apache.org Received: (qmail 19628 invoked by uid 500); 23 Nov 2014 16:52:59 -0000 Mailing-List: contact commits-help@pdfbox.apache.org; run by ezmlm Precedence: bulk List-Help: List-Unsubscribe: List-Post: List-Id: Reply-To: dev@pdfbox.apache.org Delivered-To: mailing list commits@pdfbox.apache.org Received: (qmail 19619 invoked by uid 99); 23 Nov 2014 16:52:59 -0000 Received: from athena.apache.org (HELO athena.apache.org) (140.211.11.136) by apache.org (qpsmtpd/0.29) with ESMTP; Sun, 23 Nov 2014 16:52:59 +0000 X-ASF-Spam-Status: No, hits=-2000.0 required=5.0 tests=ALL_TRUSTED X-Spam-Check-By: apache.org Received: from [140.211.11.4] (HELO eris.apache.org) (140.211.11.4) by apache.org (qpsmtpd/0.29) with ESMTP; Sun, 23 Nov 2014 16:52:58 +0000 Received: from eris.apache.org (localhost [127.0.0.1]) by eris.apache.org (Postfix) with ESMTP id 4F65823889D5; Sun, 23 Nov 2014 16:52:38 +0000 (UTC) Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit Subject: svn commit: r1641221 - in /pdfbox/trunk/fontbox/src: main/java/org/apache/fontbox/cmap/CMapParser.java test/java/org/apache/fontbox/cmap/TestCMapParser.java test/resources/cmap/CMapNoWhitespace Date: Sun, 23 Nov 2014 16:52:38 -0000 To: commits@pdfbox.apache.org From: lehmi@apache.org X-Mailer: svnmailer-1.0.9 Message-Id: <20141123165238.4F65823889D5@eris.apache.org> X-Virus-Checked: Checked by ClamAV on apache.org Author: lehmi Date: Sun Nov 23 16:52:37 2014 New Revision: 1641221 URL: http://svn.apache.org/r1641221 Log: PDFBOX-1648: improve the CMapParser to detect missing delimiters as proposed by May Gilead and Kevin Pearcey Added: pdfbox/trunk/fontbox/src/test/resources/cmap/CMapNoWhitespace - copied unchanged from r1641219, pdfbox/branches/1.8/fontbox/src/test/resources/cmap/CMapNoWhitespace Modified: pdfbox/trunk/fontbox/src/main/java/org/apache/fontbox/cmap/CMapParser.java pdfbox/trunk/fontbox/src/test/java/org/apache/fontbox/cmap/TestCMapParser.java Modified: pdfbox/trunk/fontbox/src/main/java/org/apache/fontbox/cmap/CMapParser.java URL: http://svn.apache.org/viewvc/pdfbox/trunk/fontbox/src/main/java/org/apache/fontbox/cmap/CMapParser.java?rev=1641221&r1=1641220&r2=1641221&view=diff ============================================================================== --- pdfbox/trunk/fontbox/src/main/java/org/apache/fontbox/cmap/CMapParser.java (original) +++ pdfbox/trunk/fontbox/src/main/java/org/apache/fontbox/cmap/CMapParser.java Sun Nov 23 16:52:37 2014 @@ -525,11 +525,15 @@ public class CMapParser StringBuffer buffer = new StringBuffer(); int stringByte = is.read(); - while (!isWhitespaceOrEOF(stringByte)) + while (!isWhitespaceOrEOF(stringByte) && !isDelimiter(stringByte)) { buffer.append((char) stringByte); stringByte = is.read(); } + if (isDelimiter( stringByte)) + { + is.unread(stringByte); + } retval = new LiteralName(buffer.toString()); break; } @@ -578,12 +582,12 @@ public class CMapParser // newline separator may be missing in malformed CMap files // see PDFBOX-2035 - while (!isWhitespaceOrEOF(nextByte) && nextByte != '<') + while (!isWhitespaceOrEOF(nextByte) && !isDelimiter(nextByte) && !Character.isDigit(nextByte)) { buffer.append((char) nextByte); nextByte = is.read(); } - if (nextByte == '<') + if (isDelimiter(nextByte) || Character.isDigit(nextByte)) { is.unread(nextByte); } @@ -610,6 +614,27 @@ public class CMapParser return aByte == -1 || aByte == 0x20 || aByte == 0x0D || aByte == 0x0A; } + /** Is this a standard PDF delimiter character? */ + private boolean isDelimiter(int aByte) + { + switch (aByte) + { + case '(': + case ')': + case '<': + case '>': + case '[': + case ']': + case '{': + case '}': + case '/': + case '%': + return true; + default: + return false; + } + } + private void increment(byte[] data) { increment(data, data.length - 1); Modified: pdfbox/trunk/fontbox/src/test/java/org/apache/fontbox/cmap/TestCMapParser.java URL: http://svn.apache.org/viewvc/pdfbox/trunk/fontbox/src/test/java/org/apache/fontbox/cmap/TestCMapParser.java?rev=1641221&r1=1641220&r2=1641221&view=diff ============================================================================== --- pdfbox/trunk/fontbox/src/test/java/org/apache/fontbox/cmap/TestCMapParser.java (original) +++ pdfbox/trunk/fontbox/src/test/java/org/apache/fontbox/cmap/TestCMapParser.java Sun Nov 23 16:52:37 2014 @@ -81,4 +81,18 @@ public class TestCMapParser extends Test } return code; } + + /** + * Tets the parser against a valid, but poorly formated CMap file. + * @throws IOException If something went wrong + */ + public void testParserWithPoorWhitespace() throws IOException + { + File inDir = new File("src/test/resources/cmap"); + + CMapParser parser = new CMapParser(); + CMap cMap = parser.parse( new FileInputStream(new File(inDir,"CMapNoWhitespace"))); + + assertNotNull("Failed to parse nasty CMap file", cMap); + } }