Re: [gentoo-dev] bzipped manpages

[Fabian Groffen]

On 09-01-2017 09:08:22 +0100, Jan Stary wrote:
> The particular problem I am having is that http://mdocml.bsd.lv/ ,
> my manpage formatter of choice, does deliberately not support bzip
> (or any other outside decompressors for that matter).

Attached patch works for me.  XZ should be a similar exercise, a little
cleanup would be nice then though.

Fabian

-- 
Fabian Groffen
Gentoo on a different level

--- mdocml-1.13.4/read.c
+++ mdocml-1.13.4/read.c
@@ -38,6 +38,7 @@
 #include <string.h>
 #include <unistd.h>
 #include <zlib.h>
+#include <bzlib.h>
 
 #include "mandoc_aux.h"
 #include "mandoc.h"
@@ -62,6 +62,7 @@
 	enum mandoclevel  wlevel; /* ignore messages below this */
 	int		  options; /* parser options */
 	int		  gzip; /* current input file is gzipped */
+	int		  bzip; /* current input file is bzipp2ed */
 	int		  filenc; /* encoding of the current file */
 	int		  reparse_count; /* finite interp. stack */
 	int		  line; /* line number in the file */
@@ -610,6 +611,7 @@
 		struct buf *fb, int *with_mmap)
 {
 	gzFile		 gz;
+	BZFILE		*bz;
 	size_t		 off;
 	ssize_t		 ssz;
 
@@ -629,7 +629,7 @@
 	 * concerned that this is going to tank any machines.
 	 */
 
-	if (curp->gzip == 0 && S_ISREG(st.st_mode)) {
+	if (curp->gzip == 0 && curp->bzip == 0 && S_ISREG(st.st_mode)) {
 		if (st.st_size > 0x7fffffff) {
 			mandoc_msg(MANDOCERR_TOOLARGE, curp, 0, 0, NULL);
 			return 0;
@@ -639,11 +641,15 @@
 	}
 #endif
 
+	gz = NULL;
+	bz = NULL;
 	if (curp->gzip) {
 		if ((gz = gzdopen(fd, "rb")) == NULL)
 			err((int)MANDOCLEVEL_SYSERR, "%s", file);
-	} else
-		gz = NULL;
+	} else if (curp->bzip) {
+		if ((bz = BZ2_bzdopen(fd, "rb")) == NULL)
+			err((int)MANDOCLEVEL_SYSERR, "%s", file);
+	}
 
 	/*
 	 * If this isn't a regular file (like, say, stdin), then we must
@@ -663,9 +669,13 @@
 			}
 			resize_buf(fb, 65536);
 		}
-		ssz = curp->gzip ?
-		    gzread(gz, fb->buf + (int)off, fb->sz - off) :
-		    read(fd, fb->buf + (int)off, fb->sz - off);
+		if (curp->gzip) {
+			ssz = gzread(gz, fb->buf + (int)off, fb->sz - off);
+		} else if (curp->bzip) {
+			ssz = BZ2_bzread(bz, fb->buf + (int)off, fb->sz - off);
+		} else {
+		    ssz = read(fd, fb->buf + (int)off, fb->sz - off);
+		}
 		if (ssz == 0) {
 			fb->sz = off;
 			return 1;
@@ -785,6 +795,7 @@
 	curp->file = file;
 	cp = strrchr(file, '.');
 	curp->gzip = (cp != NULL && ! strcmp(cp + 1, "gz"));
+	curp->bzip = (cp != NULL && ! strcmp(cp + 1, "bz2"));
 
 	/* First try to use the filename as it is. */
 
@@ -804,6 +815,13 @@
 			curp->gzip = 1;
 			return fd;
 		}
+		mandoc_asprintf(&cp, "%s.bz2", file);
+		fd = open(cp, O_RDONLY);
+		free(cp);
+		if (fd != -1) {
+			curp->bzip = 1;
+			return fd;
+		}
 	}
 
 	/* Neither worked, give up. */
--- mdocml-1.13.4/configure
+++ mdocml-1.13.4/configure
@@ -255,7 +255,7 @@
 fi
 
 # --- LDADD ---
-LDADD="${LDADD} ${LD_SQLITE3} ${LD_OHASH} -lz"
+LDADD="${LDADD} ${LD_SQLITE3} ${LD_OHASH} -lz -lbz2"
 echo "LDADD=\"${LDADD}\"" 1>&2
 echo "LDADD=\"${LDADD}\"" 1>&3
 echo 1>&3

signature.asc
Description: Digital signature