Merge pull request #93 from kermitt2/line-number

Line number and finalize 0.3

.gitmodules

@@ -1,4 +1,3 @@
 [submodule "xpdf-4.00"]
 	path = xpdf-4.00
 	url = https://github.com/kermitt2/xpdf-4.00
-	branch = nonumericchanamesmapping

Readme.md

@@ -21,29 +21,29 @@ The latest stable version is *0.2*. Working version (master) is *0.3*.
 General usage is as follow: 
 
 ```
- pdfalto [options] <PDF-file> [<xml-file>]
-  -f <int>               : first page to convert
-  -l <int>               : last page to convert
-  -verbose               : display pdf attributes
-  -noText                : do not extract textual objects
-  -noImage               : do not extract Images (Bitmap and Vectorial)
-  -noImageInline         : do not include images inline in the stream
-  -outline               : create an outline file xml (i.e. a table of content) as additional file
-  -annotation            : create an annotations file xml as additional file
-  -blocks                : add blocks informations whithin the structure
-  -readingOrder          : blocks follow the reading order
-  -fullFontName          : fonts names are not normalized
-  -nsURI <string>        : add the specified namespace URI
-  -opw <string>          : owner password (for encrypted files)
-  -upw <string>          : user password (for encrypted files)
-  -filesLimit <int>      : limit of asset files be extracted to the value specified
-  -q                     : don't print any messages or errors
-  -v                     : print version info
-  -h                     : print usage information
-  -help                  : print usage information
-  --help                 : print usage information
-  -?                     : print usage information
-  --saveconf <string>    : save all command line parameters in the specified XML <file>
+Usage: pdfalto [options] <PDF-file> [<xml-file>]
+  -f <int>                      : first page to convert
+  -l <int>                      : last page to convert
+  -verbose                      : display pdf attributes
+  -noImage                      : do not extract Images (Bitmap and Vectorial)
+  -noImageInline                : do not include images inline in the stream
+  -outline                      : create an outline file xml
+  -annotation                   : create an annotations file xml
+  -noLineNumbers                : do not output line numbers added in manuscript-style textual documents
+  -readingOrder                 : blocks follow the reading order
+  -noText                       : do not extract textual objects (might be useful, but non-valid ALTO)
+  -charReadingOrderAttr         : include TYPE attribute to String elements to indicate right-to-left reading order (might be useful, but non-valid ALTO)
+  -fullFontName                 : fonts names are not normalized
+  -nsURI <string>               : add the specified namespace URI
+  -opw <string>                 : owner password (for encrypted files)
+  -upw <string>                 : user password (for encrypted files)
+  -filesLimit <int>             : limit of asset files be extracted
+  -q                            : don't print any messages or errors
+  -v                            : print version info
+  -h                            : print usage information
+  -help                         : print usage information
+  --help                        : print usage information
+  -?                            : print usage information
 ```
 
 In addition to the [ALTO](https://github.com/altoxml/documentation/wiki) file describing the PDF content, the following files are generated:
@@ -93,6 +93,12 @@ The executable `pdfalto` is generated in the root directory. Additionally, this
 
 # Changes
 
+New in version 0.3 (apart various bug fixes):
+
+- line number detection: line numbers (typically added for review in manuscripts/preprints) are specifically identified and not anymore mixed with the rest of text content, they will be grouped in a separate block or, optionally, not outputted in the ALTO file (`noLineNumbers` option)
+
+- removal of `-blocks` option, the block information are always returned for ensuring ALTO validation (`<TextBlock>` element)
+
 New in version 0.2 (apart various bug fixes):
 
 - support Unicode composition of characters

install_deps.sh

@@ -18,7 +18,9 @@ DEP_INSTALL_DIR=install
 
 LIBXML_URI=http://xmlsoft.org/sources/libxml2-2.9.8.tar.gz
 FREETYPE_URI=https://download.savannah.gnu.org/releases/freetype/freetype-2.9.tar.gz
-ICU_URI=http://download.icu-project.org/files/icu4c/62.1/icu4c-62_1-src.tgz
+#ICU_URI=http://download.icu-project.org/files/icu4c/62.1/icu4c-62_1-src.tgz
+ICU_URI=https://github.com/unicode-org/icu/releases/download/release-62-2/icu4c-62_2-src.tgz
+#ICU_URI=https://github.com/unicode-org/icu/releases/download/release-66-1/icu4c-66_1-src.tgz
 
 mkdir -p $DEP_INSTALL_DIR
 

src/Parameters.cc

@@ -34,11 +34,11 @@ void Parameters::setDisplayText(GBool text) {
   unlockGlobalParams;
 }
 
-void Parameters::setDisplayBlocks(GBool block) {
+/*void Parameters::setDisplayBlocks(GBool block) {
   lockGlobalParams;
   displayBlocks = block;
   unlockGlobalParams;
-}
+}*/
 
 void Parameters::setDisplayOutline(GBool outl) {
   lockGlobalParams;
@@ -83,6 +83,12 @@ void Parameters::setOcr(GBool ocrA) {
 	unlockGlobalParams;
 }
 
+void Parameters::setNoLineNumbers(GBool noLineNumberAttrs) {
+  lockGlobalParams;
+  noLineNumbers = noLineNumberAttrs;
+  unlockGlobalParams;
+}
+
 void Parameters::saveToXML(const char *fileName,int firstPage,int lastPage){
 	char* tmp;
   	tmp=(char*)malloc(10*sizeof(char));
@@ -109,27 +115,6 @@ void Parameters::saveToXML(const char *fileName,int firstPage,int lastPage){
 	xmlAddChild(tool,version);
 	xmlAddChild(tool,desc);
 
-// * -f <int> : first page to convert<br/>
-// * -l <int> : last page to convert<br/>
-// * -verbose : display pdf attributes<br/>
-// * -noText : do not extract textual objects<br/>
-// * -noImage : do not extract images (Bitmap and Vectorial)<br/>
-// * -noImageInline : do not include images inline in the stream<br/>
-// * -outline : create an outline file xml<br/>
-// * -annots : create an annotaitons file xml<br/>
-// * -cutPages : cut all pages in separately files<br/>
-// * -blocks : add blocks informations whithin the structure<br/>
-// * -readingOrder : blocks follow the reading order<br/>	
-// * -fullFontName : fonts names are not normalized<br/>
-// * -nsURI : add the specified namespace URI<br/>
-// * -q : don't print any messages or errors<br/>
-// * -v : print copyright and version information<br/>
-// * -h : print usage information<br/>
-// * -help : print usage information<br/>
-// * --help : print usage information<br/>
-// * -? : print usage information<br/>	
-
-
 	param = xmlNewNode(NULL,(const xmlChar*)TAG_PAR_PARAM);
 	xmlNewProp(param,(const xmlChar*)"name",(const xmlChar*)"first page");
 	xmlNewProp(param,(const xmlChar*)"form",(const xmlChar*)"-f");

src/Parameters.h

@@ -31,6 +31,8 @@ class Parameters {
 	/** Destructor */
 	~Parameters();
 
+	// getters
+
 	/** Return a boolean which inform if the text is displayed 
 	 * @return <code>true</code> if the toText option is selected, <code>false</code> otherwise
 	 */
@@ -39,7 +41,7 @@ class Parameters {
 	/** Return a boolean which inform if blocks informations are diplayed
 	 * @return <code>true</code> if the blocks option is selected, <code>false</code> otherwise
 	 */
-	GBool getDisplayBlocks() { return displayBlocks;};
+	//GBool getDisplayBlocks() { return displayBlocks;};
 
 	/** Return a boolean which inform if the images are displayed
 	 * @return <code>true</code> if the noImage option is not selected, <code>false</code> otherwise
@@ -88,6 +90,13 @@ class Parameters {
 	 */
 	int getFilesCountLimit() {return filesCountLimit;}
 
+	/** Return a boolean which inform if line numbers tokens are diplayed
+	 * @return <code>true</code> if the noLineNumbers option is selected, <code>false</code> otherwise
+	 */
+	GBool getNoLineNumbers() { return noLineNumbers;};
+
+	// setters
+
 	/** Modify the boolean which inform if the images are displayed
 	 * @param noImage <code>true</code> if the noImage option is not selected, <code>false</code> otherwise
 	 */
@@ -101,7 +110,7 @@ class Parameters {
 	/** Modify the boolean which inform if blocks informations are diplayed
 	 * @param noblock <code>true</code> if the blocks option is selected, <code>false</code> otherwise
 	 */	
-	void setDisplayBlocks(GBool noblock);
+	//void setDisplayBlocks(GBool noblock);
 
 	/** Modify the boolean which inform if the bookmark is displayed
 	 * @param outline <code>true</code> if the outline option is selected, <code>false</code> otherwise
@@ -140,6 +149,11 @@ class Parameters {
 	void setOcr(GBool ocrA);
 
 	void setFilesCountLimit(int count);
+
+	/** Modify the boolean which inform if line numbers must be diplayed
+	 * @param noLineNumberAttrs <code>true</code> if the noLineNumbers option is selected, <code>false</code> otherwise
+	 */	
+	void setNoLineNumbers(GBool noLineNumberAttrs);
 
 	void saveToXML(const char *fileName,int firstPage,int lastPage);
 
@@ -150,7 +164,7 @@ class Parameters {
 	/** The value of the noText option */
 	GBool displayText;
 	/** The value of the blocks option */
-	GBool displayBlocks;
+	//GBool displayBlocks;
 	/** The value of the outline option */
 	GBool displayOutline;
 	/** The value of the cutPages option */
@@ -167,7 +181,8 @@ class Parameters {
 	GBool ocr;
 	/** the count limit of files */
 	int filesCountLimit;
-
+  	/** PL: the value of the noLineNumbers option*/
+  	GBool noLineNumbers;
 };
 
 #endif /*PARAMETERS_H_*/