On Tue, Jan 26, 2016 at 02:46:29PM +0100, Simon Ruderich wrote: > Hi, > > I'm using GNU screen's hardcopy function to dump the current > screen content to a file. However the resulting file is encoded > in ISO-8859-1 although my current locale is UTF-8. This causes > corruption for characters which are not representable in > ISO-8859-1.
Hello again,
It's not actually using ISO-8859-1, but instead printing the
first byte of ->image which seems to be the unicode code point.
image.h:
/* structure representing single cell of terminal */
struct mchar {
uint32_t image; /* actual letter like a, b, c ... */
[...]
};
fileio.c WriteFile():
for (i = 0; i < fore->w_height; i++) {
p = fore->w_mlines[i].image;
for (k = fore->w_width - 1; k >= 0 && p[k] == ' '; k--) ;
for (j = 0; j <= k; j++)
putc(p[j], f);
putc('\n', f);
}
This obviously doesn't work for characters > 255 which caused the
garbled display for me.
The attached patch should fix the issue. However somebody should
verify my assumptions:
I'm not 100% sure that ->image is actually the unicode code
point.
Double-width characters are followed by a character with ->image
= 0xff and ->font = 0xff. I assumed that this means the character
is a filler character to handle the fixed screen width correctly,
but I'm not entirely sure. Is there a function/constant to check
for fillers like this? Hard-coding 0xff doesn't sound like a good
idea.
I don't know how the fontp parameter of EncodeChar() is used:
int EncodeChar(char *bp, int c, int encoding, int *fontp)
Passing NULL seems to work though.
Regards
Simon
PS: The Git repository contains a lot of commits since the last
release. A new release of GNU Screen sounds like a good idea to
get those fixes/improvements distributed.
--
+ privacy is necessary
+ using gnupg http://gnupg.org
+ public key id: 0x92FEFDB7E44C32F9
From 1aa921e2e56867cc933973d96a786a83eca8bf3c Mon Sep 17 00:00:00 2001
From: Simon Ruderich <si...@ruderich.org>
Date: Sat, 6 Feb 2016 16:26:03 +0100
Subject: [PATCH] :hardcopy: handle encoding
Previously only the first byte of the Unicode code point was
written to the hardcopy file.
---
src/fileio.c | 24 +++++++++++++++++++++---
src/image.h | 2 +-
2 files changed, 22 insertions(+), 4 deletions(-)
diff --git a/src/fileio.c b/src/fileio.c
index 5dc1797..6cd21ac 100644
--- a/src/fileio.c
+++ b/src/fileio.c
@@ -42,6 +42,7 @@
#include "misc.h"
#include "process.h"
#include "termcap.h"
+#include "encoding.h"
static char *CatExtra(char *, char *);
static char *findrcfile(char *);
@@ -304,6 +305,21 @@ void RcLine(char *ubuf, int ubufl)
EffectiveAclUser = 0;
}
+
+static void putc_encoded(FILE *f, uint32_t c, uint32_t font, int encoding) {
+ /* Filler character which is used for double-width characters. */
+ if (c == 0xff && font == 0xff)
+ return;
+
+ char buf[10];
+ int length = EncodeChar(buf, c, encoding, NULL);
+ if (length < 0) {
+ return;
+ }
+ buf[length] = 0;
+ fputs(buf, f);
+}
+
/*
* needs display for copybuffer access and termcap dumping
*/
@@ -315,7 +331,6 @@ void WriteFile(struct acluser *user, char *fn, int dump)
* dump==1: scrollback,
*/
int i, j, k;
- uint32_t *p;
char *c;
FILE *f;
char fnbuf[FILENAME_MAX];
@@ -384,6 +399,7 @@ void WriteFile(struct acluser *user, char *fn, int dump)
if (f == NULL) {
UserReturn(0);
} else {
+ uint32_t *p, *pf;
switch (dump) {
case DUMP_HARDCOPY:
case DUMP_SCROLLBACK:
@@ -398,17 +414,19 @@ void WriteFile(struct acluser *user, char *fn, int dump)
if (dump == DUMP_SCROLLBACK) {
for (i = 0; i < fore->w_histheight; i++) {
p = (WIN(i)->image);
+ pf = WIN(i)->font;
for (k = fore->w_width - 1; k >= 0 && p[k] == ' '; k--) ;
for (j = 0; j <= k; j++)
- putc(p[j], f);
+ putc_encoded(f, p[j], pf[j], fore->w_encoding);
putc('\n', f);
}
}
for (i = 0; i < fore->w_height; i++) {
p = fore->w_mlines[i].image;
+ pf = fore->w_mlines[i].font;
for (k = fore->w_width - 1; k >= 0 && p[k] == ' '; k--) ;
for (j = 0; j <= k; j++)
- putc(p[j], f);
+ putc_encoded(f, p[j], pf[j], fore->w_encoding);
putc('\n', f);
}
break;
diff --git a/src/image.h b/src/image.h
index 9ce9b0e..487dfc2 100644
--- a/src/image.h
+++ b/src/image.h
@@ -34,7 +34,7 @@
/* structure representing single cell of terminal */
struct mchar {
- uint32_t image; /* actual letter like a, b, c ... */
+ uint32_t image; /* actual letter like a, b, c ... as Unicode code point */
uint32_t attr; /* attributes - bold, standout etc. */
uint32_t font; /* font :) */
uint32_t fontx; /* extended font; TODO: remove - merge with font */
--
2.7.0
signature.asc
Description: PGP signature
