gnu: libxslt: Make generated documentation reproducible.

* gnu/packages/patches/libxslt-generated-ids.patch: New file.
* gnu/packages/patches/libxslt-remove-date-timestamps.patch: Likewise.
* gnu/packages/xml.scm (libxslt)[source]: Use them.
* gnu/local.mk (dist_patch_DATA): Add them.

4 files changed, 245 insertions, 1 deletions

diff --git a/gnu/local.mk b/gnu/local.mk
index 8d945e835d..da377fdbb3 100644
--- a/gnu/local.mk
+++ b/gnu/local.mk
@@ -603,6 +603,8 @@ dist_patch_DATA =						\
   gnu/packages/patches/libwmf-CVE-2015-4695.patch		\
   gnu/packages/patches/libwmf-CVE-2015-4696.patch		\
   gnu/packages/patches/libxslt-CVE-2015-7995.patch		\
+  gnu/packages/patches/libxslt-generated-ids.patch		\
+  gnu/packages/patches/libxslt-remove-date-timestamps.patch	\
   gnu/packages/patches/lirc-localstatedir.patch			\
   gnu/packages/patches/libpthread-glibc-preparation.patch	\
   gnu/packages/patches/lm-sensors-hwmon-attrs.patch		\
diff --git a/gnu/packages/patches/libxslt-generated-ids.patch b/gnu/packages/patches/libxslt-generated-ids.patch
new file mode 100644
index 0000000000..4273875c7c
--- /dev/null
+++ b/gnu/packages/patches/libxslt-generated-ids.patch
@@ -0,0 +1,173 @@
+This makes generated IDs deterministic.
+
+Written by Daniel Veillard.
+
+This should be fixed in next release (2.29).
+See https://bugzilla.gnome.org/show_bug.cgi?id=751621.
+
+diff --git a/libxslt/functions.c b/libxslt/functions.c
+index 6448bde..5b00a6d 100644
+--- a/libxslt/functions.c
++++ b/libxslt/functions.c
+@@ -651,6 +651,63 @@ xsltFormatNumberFunction(xmlXPathParserContextPtr ctxt, int nargs)
+ }
+ 
+ /**
++ * xsltCleanupIds:
++ * @ctxt: the transformation context
++ * @root: the root of the resulting document
++ *
++ * This clean up ids which may have been saved in Element contents
++ * by xsltGenerateIdFunction() to provide stable IDs on elements.
++ *
++ * Returns the number of items cleaned or -1 in case of error
++ */
++int
++xsltCleanupIds(xsltTransformContextPtr ctxt, xmlNodePtr root) {
++    xmlNodePtr cur;
++    int count = 0;
++
++    if ((ctxt == NULL) || (root == NULL))
++        return(-1);
++    if (root->type != XML_ELEMENT_NODE)
++        return(-1);
++
++    cur = root;
++    while (cur != NULL) {
++	if (cur->type == XML_ELEMENT_NODE) {
++	    if (cur->content != NULL) {
++	        cur->content = NULL;
++		count++;
++	    }
++	    if (cur->children != NULL) {
++		cur = cur->children;
++		continue;
++	    }
++	}
++	if (cur->next != NULL) {
++	    cur = cur->next;
++	    continue;
++	}
++	do {
++	    cur = cur->parent;
++	    if (cur == NULL)
++		break;
++	    if (cur == (xmlNodePtr) root) {
++		cur = NULL;
++		break;
++	    }
++	    if (cur->next != NULL) {
++		cur = cur->next;
++		break;
++	    }
++	} while (cur != NULL);
++    }
++
++fprintf(stderr, "Attributed %d IDs for element, cleaned up %d\n",
++        ctxt->nextid, count);
++
++    return(count);
++}
++
++/**
+  * xsltGenerateIdFunction:
+  * @ctxt:  the XPath Parser context
+  * @nargs:  the number of arguments
+@@ -701,7 +758,39 @@ xsltGenerateIdFunction(xmlXPathParserContextPtr ctxt, int nargs){
+     if (obj)
+         xmlXPathFreeObject(obj);
+ 
+-    val = (long)((char *)cur - (char *)&base_address);
++    /*
++     * Try to provide stable ID for generated document:
++     *   - usually ID are computed to be placed on elements via attributes
++     *     so using the element as the node for the ID
++     *   - the cur->content should be a correct placeholder for this, we use
++     *     it to hold element node numbers in xmlXPathOrderDocElems to
++     *     speed up XPath too
++     *   - xsltCleanupIds() clean them up before handing the XSLT output
++     *     to the API client.
++     *   - other nodes types use the node address method but that should
++     *     not end up in resulting document ID
++     *   - we can enable this by default without risk of performance issues
++     *     only the one pass xsltCleanupIds() is added
++     */
++    if (cur->type == XML_ELEMENT_NODE) {
++        if (cur->content == NULL) {
++	    xsltTransformContextPtr tctxt;
++
++	    tctxt = xsltXPathGetTransformContext(ctxt);
++	    if (tctxt == NULL) {
++		val = (long)((char *)cur - (char *)&base_address);
++	    } else {
++		tctxt->nextid++;
++		val = tctxt->nextid;
++		cur->content = (void *) (val);
++	    }
++	} else {
++	    val = (long) cur->content;
++	}
++    } else {
++	val = (long)((char *)cur - (char *)&base_address);
++    }
++
+     if (val >= 0) {
+       sprintf((char *)str, "idp%ld", val);
+     } else {
+diff --git a/libxslt/functions.h b/libxslt/functions.h
+index e0e0bf9..4a1e163 100644
+--- a/libxslt/functions.h
++++ b/libxslt/functions.h
+@@ -64,6 +64,13 @@ XSLTPUBFUN void XSLTCALL
+ 					 int nargs);
+ 
+ /*
++ * Cleanup for ID generation
++ */
++XSLTPUBFUN int XSLTCALL
++	xsltCleanupIds			(xsltTransformContextPtr ctxt,
++					 xmlNodePtr root);
++
++/*
+  * And the registration
+  */
+ 
+diff --git a/libxslt/transform.c b/libxslt/transform.c
+index 24f9eb2..2bdf6bf 100644
+--- a/libxslt/transform.c
++++ b/libxslt/transform.c
+@@ -700,6 +700,7 @@ xsltNewTransformContext(xsltStylesheetPtr style, xmlDocPtr doc) {
+     cur->traceCode = (unsigned long*) &xsltDefaultTrace;
+     cur->xinclude = xsltGetXIncludeDefault();
+     cur->keyInitLevel = 0;
++    cur->nextid = 0;
+ 
+     return(cur);
+ 
+@@ -6092,6 +6093,13 @@ xsltApplyStylesheetInternal(xsltStylesheetPtr style, xmlDocPtr doc,
+     if (root != NULL) {
+         const xmlChar *doctype = NULL;
+ 
++        /*
++	 * cleanup ids which may have been saved in Elements content ptrs
++	 */
++	if (ctxt->nextid != 0) {
++	    xsltCleanupIds(ctxt, root);
++	}
++
+         if ((root->ns != NULL) && (root->ns->prefix != NULL))
+ 	    doctype = xmlDictQLookup(ctxt->dict, root->ns->prefix, root->name);
+ 	if (doctype == NULL)
+diff --git a/libxslt/xsltInternals.h b/libxslt/xsltInternals.h
+index 95e8fe6..8eedae4 100644
+--- a/libxslt/xsltInternals.h
++++ b/libxslt/xsltInternals.h
+@@ -1786,6 +1786,8 @@ struct _xsltTransformContext {
+     int funcLevel;      /* Needed to catch recursive functions issues */
+     int maxTemplateDepth;
+     int maxTemplateVars;
++
++    unsigned long nextid;/* for generating stable ids */
+ };
+ 
+ /**
diff --git a/gnu/packages/patches/libxslt-remove-date-timestamps.patch b/gnu/packages/patches/libxslt-remove-date-timestamps.patch
new file mode 100644
index 0000000000..51470d0847
--- /dev/null
+++ b/gnu/packages/patches/libxslt-remove-date-timestamps.patch
@@ -0,0 +1,66 @@
+Use deterministic SOURCE_DATE_EPOCH for embedded timestamps in generated documentation.
+
+Written by Eduard Sanou.
+
+https://bugzilla.gnome.org/show_bug.cgi?id=758148
+
+--- libxslt-1.1.28.orig/libexslt/date.c
++++ libxslt-1.1.28/libexslt/date.c
+@@ -46,6 +46,7 @@
+ #include "exslt.h"
+ 
+ #include <string.h>
++#include <errno.h>
+ 
+ #ifdef HAVE_MATH_H
+ #include <math.h>
+@@ -747,21 +748,46 @@ static exsltDateValPtr
+ exsltDateCurrent (void)
+ {
+     struct tm localTm, gmTm;
++    struct tm *tb = NULL;
+     time_t secs;
+     int local_s, gm_s;
+     exsltDateValPtr ret;
++    char *source_date_epoch;
+ 
+     ret = exsltDateCreateDate(XS_DATETIME);
+     if (ret == NULL)
+         return NULL;
+ 
+-    /* get current time */
+     secs    = time(NULL);
++    /*
++     * Allow the date and time to be set externally by an exported
++     * environment variable to enable reproducible builds.
++     */
++    source_date_epoch = getenv("SOURCE_DATE_EPOCH");
++    if (source_date_epoch) {
++	errno = 0;
++	secs = (time_t) strtol (source_date_epoch, NULL, 10);
++	if (errno == 0) {
++	    tb = gmtime(&secs);
++	    if (tb == NULL) {
++	    /* SOURCE_DATE_EPOCH is not a valid date */
++		return NULL;
++	    } else {
++		localTm = *tb;
++	    }
++	} else {
++	    /* SOURCE_DATE_EPOCH is not a valid number */
++	    return NULL;
++	}
++    } else {
++	/* get current time */
+ #if HAVE_LOCALTIME_R
+-    localtime_r(&secs, &localTm);
++	localtime_r(&secs, &localTm);
+ #else
+-    localTm = *localtime(&secs);
++	localTm = *localtime(&secs);
+ #endif
++    }
++
+ 
+     /* get real year, not years since 1900 */
+     ret->value.date.year = localTm.tm_year + 1900;
diff --git a/gnu/packages/xml.scm b/gnu/packages/xml.scm
index 838ce34364..538996f88f 100644
--- a/gnu/packages/xml.scm
+++ b/gnu/packages/xml.scm
@@ -7,6 +7,7 @@
 ;;; Copyright © 2015, 2016 Mark H Weaver <mhw@netris.org>
 ;;; Copyright © 2015 Efraim Flashner <efraim@flashner.co.il>
 ;;; Copyright © 2015 Raimon Grau <raimonster@gmail.com>
+;;; Copyright © 2016 Mathieu Lirzin <mthl@gnu.org>
 ;;;
 ;;; This file is part of GNU Guix.
 ;;;
@@ -131,7 +132,9 @@ project (but it is usable outside of the Gnome platform).")
              (sha256
               (base32
                "13029baw9kkyjgr7q3jccw2mz38amq7mmpr5p3bh775qawd1bisz"))
-             (patches (search-patches "libxslt-CVE-2015-7995.patch"))))
+             (patches (search-patches "libxslt-generated-ids.patch"
+                                      "libxslt-remove-date-timestamps.patch"
+                                      "libxslt-CVE-2015-7995.patch"))))
     (build-system gnu-build-system)
     (home-page "http://xmlsoft.org/XSLT/index.html")
     (synopsis "C library for applying XSLT stylesheets to XML documents")