Merge pull request #39 from hafen/master

v0.75.2

NEWS.md

@@ -1,6 +1,8 @@
-Version 0.75.1.6
+Version 0.75
 ----------------------------------------------------------------------
 
+- fix for internal C methods conflicting with digest md5 (0.75.2)
+- fix reduce issue when incrementally building lists of `reduce.values` (0.75.2)
 - provide serialization for simple environments
 - update so that output to non-standard file URIs like s3 work in `rhwatch()`
 - update build script
@@ -15,10 +17,6 @@ Version 0.75.1.6
 - update all deprecated hadoop api calls
 - update PersonalServer `ls` to handle non-default Hadoop URIs differently
 - add `_meta` to ignored RHIPE files
-
-Version 0.75.1
-----------------------------------------------------------------------
-
 - fix build.xml to be more linux-friendly
 - `rherrors` can read output of `rhwatch(..., read=FALSE)` to read the errors folder using the new dump frames options
 - `rhJobInfo`, `rhstatus` and `rhwatch` correctly get the jobid (uses the Java MapReduce API)

build.xml

@@ -7,7 +7,7 @@
     Targets that begin with an '_' (e.g. _build-hadoop-1) are not designed to run as a standalone target
 
     -->
-    <property name="rhipe.version" value="0.75.1.6"/>
+    <property name="rhipe.version" value="0.75.2"/>
 
     <property name="maven.project.name" value="rhipe-java"/>
     <property name="maven.dl.dir" value="conf/maven"/>

pom.xml

@@ -4,10 +4,10 @@
 
     <groupId>org.godhuli.rhipe</groupId>
     <artifactId>rhipe-java</artifactId>
-    <version>0.75.1.6</version>
+    <version>0.75.2</version>
     <packaging>jar</packaging>
     <name>Rhipe</name>
-    <url>https://github.com/saptarshiguha/RHIPE</url>
+    <url>https://github.com/tesseradata/RHIPE</url>
 
     <properties>
         <!--<hadoop.version>2.3.0-cdh5.0.0</hadoop.version>-->

src/main/C/md5.c

@@ -37,6 +37,8 @@
   <ghost@aladdin.com>.  Other authors are noted in the change history
   that follows (in reverse chronological order):
 
+  2015-11-17 amw Changed all functions called md5_* to md5_*_rh to prevent
+   conflicts with digest library functions of the same name in R.
   2002-04-13 lpd Clarified derivation from RFC 1321; now handles byte order
 	either statically or dynamically; added missing #include <string.h>
 	in library.
@@ -129,7 +131,7 @@
 
 
 static void
-md5_process(md5_state_t *pms, const md5_byte_t *data /*[64]*/)
+md5_process_rh(md5_state_t *pms, const md5_byte_t *data /*[64]*/)
 {
     md5_word_t
 	a = pms->abcd[0], b = pms->abcd[1],
@@ -310,7 +312,7 @@ md5_process(md5_state_t *pms, const md5_byte_t *data /*[64]*/)
 }
 
 void
-md5_init(md5_state_t *pms)
+md5_init_rh(md5_state_t *pms)
 {
     pms->count[0] = pms->count[1] = 0;
     pms->abcd[0] = 0x67452301;
@@ -320,7 +322,7 @@ md5_init(md5_state_t *pms)
 }
 
 void
-md5_append(md5_state_t *pms, const md5_byte_t *data, int nbytes)
+md5_append_rh(md5_state_t *pms, const md5_byte_t *data, int nbytes)
 {
     const md5_byte_t *p = data;
     int left = nbytes;
@@ -345,20 +347,20 @@ md5_append(md5_state_t *pms, const md5_byte_t *data, int nbytes)
 	    return;
 	p += copy;
 	left -= copy;
-	md5_process(pms, pms->buf);
+	md5_process_rh(pms, pms->buf);
     }
 
     /* Process full blocks. */
     for (; left >= 64; p += 64, left -= 64)
-	md5_process(pms, p);
+	md5_process_rh(pms, p);
 
     /* Process a final partial block. */
     if (left)
 	memcpy(pms->buf, p, left);
 }
 
 void
-md5_finish(md5_state_t *pms, md5_byte_t digest[16])
+md5_finish_rh(md5_state_t *pms, md5_byte_t digest[16])
 {
     static const md5_byte_t pad[64] = {
 	0x80, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
@@ -373,9 +375,9 @@ md5_finish(md5_state_t *pms, md5_byte_t digest[16])
     for (i = 0; i < 8; ++i)
 	data[i] = (md5_byte_t)(pms->count[i >> 2] >> ((i & 3) << 3));
     /* Pad to 56 bytes mod 64. */
-    md5_append(pms, pad, ((55 - (pms->count[0] >> 3)) & 63) + 1);
+    md5_append_rh(pms, pad, ((55 - (pms->count[0] >> 3)) & 63) + 1);
     /* Append the length. */
-    md5_append(pms, data, 8);
+    md5_append_rh(pms, data, 8);
     for (i = 0; i < 16; ++i)
 	digest[i] = (md5_byte_t)(pms->abcd[i >> 2] >> ((i & 3) << 3));
 }

src/main/C/md5.h

@@ -37,6 +37,8 @@
   <ghost@aladdin.com>.  Other authors are noted in the change history
   that follows (in reverse chronological order):
 
+  2015-11-17 amw Changed all functions called md5_* to md5_*_rh to prevent
+   conflicts with digest library functions of the same name in R.
   2002-04-13 lpd Removed support for non-ANSI compilers; removed
 	references to Ghostscript; clarified derivation from RFC 1321;
 	now handles byte order either statically or dynamically.
@@ -76,13 +78,13 @@ extern "C"
 #endif
 
 /* Initialize the algorithm. */
-void md5_init(md5_state_t *pms);
+void md5_init_rh(md5_state_t *pms);
 
 /* Append a string to the message. */
-void md5_append(md5_state_t *pms, const md5_byte_t *data, int nbytes);
+void md5_append_rh(md5_state_t *pms, const md5_byte_t *data, int nbytes);
 
 /* Finish the message and return the digest. */
-void md5_finish(md5_state_t *pms, md5_byte_t digest[16]);
+void md5_finish_rh(md5_state_t *pms, md5_byte_t digest[16]);
 
 #ifdef __cplusplus
 }  /* end extern "C" */

src/main/C/reducer.cc

@@ -121,7 +121,7 @@ const int reducer_run(void){
       if(redbuf_cnt == REDBUFFER){
 	// Case 1. The reduce.values has reached the critical length
 	// for evaluation
-	Rf_setVar(Rf_install("reduce.values"),vvector,R_GlobalEnv);
+	Rf_setVar(Rf_install("reduce.values"),Rf_duplicate(vvector),R_GlobalEnv);
 	WRAP_R_EVAL(reduce,NULL, &Rerr);
 	redbuf_cnt=0;
 	bytes_read = 0;

src/main/C/rhooks.cc

@@ -547,9 +547,9 @@ SEXP readSQFromPipe(SEXP jcmd, SEXP buf, SEXP verb) {
   SEXP md5(SEXP aRaw,SEXP len){
     md5_state_t state;
     md5_byte_t digest[16];
-    md5_init(&state);
-    md5_append(&state, (const md5_byte_t *)RAW(aRaw), INTEGER(len)[0]);
-    md5_finish(&state, digest);
+    md5_init_rh(&state);
+    md5_append_rh(&state, (const md5_byte_t *)RAW(aRaw), INTEGER(len)[0]);
+    md5_finish_rh(&state, digest);
     char hex_output[16*2 + 1];
     for (int di = 0; di < 16; ++di)
       sprintf(hex_output + di * 2, "%02x", digest[di]);