From: Jonathan Nieder <jrnieder@gmail.com>
To: Ramkumar Ramachandra <artagnon@gmail.com>
Cc: Git Mailing List <git@vger.kernel.org>,
David Michael Barr <david.barr@cordelta.com>,
Sverre Rabbelier <srabbelier@gmail.com>,
Junio C Hamano <gitster@pobox.com>
Subject: [PATCH 06/10] Add stream helper library
Date: Mon, 9 Aug 2010 17:39:43 -0500 [thread overview]
Message-ID: <20100809223943.GB4429@burratino> (raw)
In-Reply-To: <20100809215719.GA4203@burratino>
From: David Barr <david.barr@cordelta.com>
This library provides thread-unsafe fgets()- and fread()-like
functions where the caller does not have to supply a buffer. It
maintains a couple of static buffers and provides an API to use
them.
[rr: allow input from files other than stdin]
[jn: with tests, documentation, and error handling improvements]
Signed-off-by: David Barr <david.barr@cordelta.com>
Signed-off-by: Ramkumar Ramachandra <artagnon@gmail.com>
Signed-off-by: Jonathan Nieder <jrnieder@gmail.com>
---
New tests and API docs. The return value from buffer_deinit
can be used to check for errors now (I found this useful when
writing tests).
.gitignore | 1 +
Makefile | 8 +++-
t/t0080-vcs-svn.sh | 54 ++++++++++++++++++++++++++
test-line-buffer.c | 46 ++++++++++++++++++++++
vcs-svn/line_buffer.c | 97 +++++++++++++++++++++++++++++++++++++++++++++++
vcs-svn/line_buffer.h | 12 ++++++
vcs-svn/line_buffer.txt | 58 ++++++++++++++++++++++++++++
7 files changed, 274 insertions(+), 2 deletions(-)
create mode 100644 test-line-buffer.c
create mode 100644 vcs-svn/line_buffer.c
create mode 100644 vcs-svn/line_buffer.h
create mode 100644 vcs-svn/line_buffer.txt
diff --git a/.gitignore b/.gitignore
index 9f109db..8c0512e 100644
--- a/.gitignore
+++ b/.gitignore
@@ -166,6 +166,7 @@
/test-dump-cache-tree
/test-genrandom
/test-index-version
+/test-line-buffer
/test-match-trees
/test-obj-pool
/test-parse-options
diff --git a/Makefile b/Makefile
index 24103c9..a76cce5 100644
--- a/Makefile
+++ b/Makefile
@@ -408,6 +408,7 @@ TEST_PROGRAMS_NEED_X += test-date
TEST_PROGRAMS_NEED_X += test-delta
TEST_PROGRAMS_NEED_X += test-dump-cache-tree
TEST_PROGRAMS_NEED_X += test-genrandom
+TEST_PROGRAMS_NEED_X += test-line-buffer
TEST_PROGRAMS_NEED_X += test-match-trees
TEST_PROGRAMS_NEED_X += test-obj-pool
TEST_PROGRAMS_NEED_X += test-parse-options
@@ -1743,7 +1744,7 @@ ifndef NO_CURL
endif
XDIFF_OBJS = xdiff/xdiffi.o xdiff/xprepare.o xdiff/xutils.o xdiff/xemit.o \
xdiff/xmerge.o xdiff/xpatience.o
-VCSSVN_OBJS = vcs-svn/string_pool.o
+VCSSVN_OBJS = vcs-svn/string_pool.o vcs-svn/line_buffer.o
OBJECTS := $(GIT_OBJS) $(XDIFF_OBJS) $(VCSSVN_OBJS)
dep_files := $(foreach f,$(OBJECTS),$(dir $f).depend/$(notdir $f).d)
@@ -1867,7 +1868,8 @@ xdiff-interface.o $(XDIFF_OBJS): \
xdiff/xutils.h xdiff/xprepare.h xdiff/xdiffi.h xdiff/xemit.h
$(VCSSVN_OBJS): \
- vcs-svn/obj_pool.h vcs-svn/trp.h vcs-svn/string_pool.h
+ vcs-svn/obj_pool.h vcs-svn/trp.h vcs-svn/string_pool.h \
+ vcs-svn/line_buffer.h
endif
exec_cmd.s exec_cmd.o: EXTRA_CPPFLAGS = \
@@ -2016,6 +2018,8 @@ test-date$X: date.o ctype.o
test-delta$X: diff-delta.o patch-delta.o
+test-line-buffer$X: vcs-svn/lib.a
+
test-parse-options$X: parse-options.o
test-string-pool$X: vcs-svn/lib.a
diff --git a/t/t0080-vcs-svn.sh b/t/t0080-vcs-svn.sh
index 99a314b..d3225ad 100755
--- a/t/t0080-vcs-svn.sh
+++ b/t/t0080-vcs-svn.sh
@@ -76,6 +76,60 @@ test_expect_success 'obj pool: high-water mark' '
test_cmp expected actual
'
+test_expect_success 'line buffer' '
+ echo HELLO >expected1 &&
+ printf "%s\n" "" HELLO >expected2 &&
+ echo >expected3 &&
+ printf "%s\n" "" Q | q_to_nul >expected4 &&
+ printf "%s\n" foo "" >expected5 &&
+ printf "%s\n" "" foo >expected6 &&
+
+ test-line-buffer <<-\EOF >actual1 &&
+ 5
+ HELLO
+ EOF
+
+ test-line-buffer <<-\EOF >actual2 &&
+ 0
+
+ 5
+ HELLO
+ EOF
+
+ q_to_nul <<-\EOF |
+ 1
+ Q
+ EOF
+ test-line-buffer >actual3 &&
+
+ q_to_nul <<-\EOF |
+ 0
+
+ 1
+ Q
+ EOF
+ test-line-buffer >actual4 &&
+
+ test-line-buffer <<-\EOF >actual5 &&
+ 5
+ foo
+ EOF
+
+ test-line-buffer <<-\EOF >actual6 &&
+ 0
+
+ 5
+ foo
+ EOF
+
+ test_cmp expected1 actual1 &&
+ test_cmp expected2 actual2 &&
+ test_cmp expected3 actual3 &&
+ test_cmp expected4 actual4 &&
+ test_cmp expected5 actual5 &&
+ test_cmp expected6 actual6
+'
+
test_expect_success 'string pool' '
echo a does not equal b >expected.differ &&
echo a equals a >expected.match &&
diff --git a/test-line-buffer.c b/test-line-buffer.c
new file mode 100644
index 0000000..c11bf7f
--- /dev/null
+++ b/test-line-buffer.c
@@ -0,0 +1,46 @@
+/*
+ * test-line-buffer.c: code to exercise the svn importer's input helper
+ *
+ * Input format:
+ * number NL
+ * (number bytes) NL
+ * number NL
+ * ...
+ */
+
+#include "git-compat-util.h"
+#include "vcs-svn/line_buffer.h"
+
+static uint32_t strtouint32(const char *s)
+{
+ char *end;
+ uintmax_t n = strtoumax(s, &end, 10);
+ if (*s == '\0' || *end != '\0')
+ die("invalid count: %s", s);
+ return (uint32_t) n;
+}
+
+int main(int argc, char *argv[])
+{
+ char *s;
+
+ if (argc != 1)
+ usage("test-line-buffer < input.txt");
+ if (buffer_init(NULL))
+ die_errno("open error");
+ while ((s = buffer_read_line())) {
+ s = buffer_read_string(strtouint32(s));
+ fputs(s, stdout);
+ fputc('\n', stdout);
+ buffer_skip_bytes(1);
+ if (!(s = buffer_read_line()))
+ break;
+ buffer_copy_bytes(strtouint32(s) + 1);
+ }
+ if (buffer_deinit())
+ die("input error");
+ if (ferror(stdout))
+ die("output error");
+ buffer_reset();
+ return 0;
+}
diff --git a/vcs-svn/line_buffer.c b/vcs-svn/line_buffer.c
new file mode 100644
index 0000000..1543567
--- /dev/null
+++ b/vcs-svn/line_buffer.c
@@ -0,0 +1,97 @@
+/*
+ * Licensed under a two-clause BSD-style license.
+ * See LICENSE for details.
+ */
+
+#include "git-compat-util.h"
+#include "line_buffer.h"
+#include "obj_pool.h"
+
+#define LINE_BUFFER_LEN 10000
+#define COPY_BUFFER_LEN 4096
+
+/* Create memory pool for char sequence of known length */
+obj_pool_gen(blob, char, 4096)
+
+static char line_buffer[LINE_BUFFER_LEN];
+static char byte_buffer[COPY_BUFFER_LEN];
+static FILE *infile;
+
+int buffer_init(const char *filename)
+{
+ infile = filename ? fopen(filename, "r") : stdin;
+ if (!infile)
+ return -1;
+ return 0;
+}
+
+int buffer_deinit(void)
+{
+ int err;
+ if (infile == stdin)
+ return ferror(infile);
+ err = ferror(infile);
+ err |= fclose(infile);
+ return err;
+}
+
+/* Read a line without trailing newline. */
+char *buffer_read_line(void)
+{
+ char *end;
+ if (!fgets(line_buffer, sizeof(line_buffer), infile))
+ /* Error or data exhausted. */
+ return NULL;
+ end = line_buffer + strlen(line_buffer);
+ if (end[-1] == '\n')
+ end[-1] = '\0';
+ else if (feof(infile))
+ ; /* No newline at end of file. That's fine. */
+ else
+ /*
+ * Line was too long.
+ * There is probably a saner way to deal with this,
+ * but for now let's return an error.
+ */
+ return NULL;
+ return line_buffer;
+}
+
+char *buffer_read_string(uint32_t len)
+{
+ char *s;
+ blob_free(blob_pool.size);
+ s = blob_pointer(blob_alloc(len + 1));
+ s[fread(s, 1, len, infile)] = '\0';
+ return ferror(infile) ? NULL : s;
+}
+
+void buffer_copy_bytes(uint32_t len)
+{
+ uint32_t in;
+ while (len > 0 && !feof(infile) && !ferror(infile)) {
+ in = len < COPY_BUFFER_LEN ? len : COPY_BUFFER_LEN;
+ in = fread(byte_buffer, 1, in, infile);
+ len -= in;
+ fwrite(byte_buffer, 1, in, stdout);
+ if (ferror(stdout)) {
+ buffer_skip_bytes(len);
+ return;
+ }
+ }
+}
+
+void buffer_skip_bytes(uint32_t len)
+{
+ uint32_t in;
+ while (len > 0 && !feof(infile) && !ferror(infile)) {
+ in = len < COPY_BUFFER_LEN ? len : COPY_BUFFER_LEN;
+ in = fread(byte_buffer, 1, in, infile);
+ len -= in;
+ }
+}
+
+void buffer_reset(void)
+{
+ blob_reset();
+}
diff --git a/vcs-svn/line_buffer.h b/vcs-svn/line_buffer.h
new file mode 100644
index 0000000..9c78ae1
--- /dev/null
+++ b/vcs-svn/line_buffer.h
@@ -0,0 +1,12 @@
+#ifndef LINE_BUFFER_H_
+#define LINE_BUFFER_H_
+
+int buffer_init(const char *filename);
+int buffer_deinit(void);
+char *buffer_read_line(void);
+char *buffer_read_string(uint32_t len);
+void buffer_copy_bytes(uint32_t len);
+void buffer_skip_bytes(uint32_t len);
+void buffer_reset(void);
+
+#endif
diff --git a/vcs-svn/line_buffer.txt b/vcs-svn/line_buffer.txt
new file mode 100644
index 0000000..8906fb1
--- /dev/null
+++ b/vcs-svn/line_buffer.txt
@@ -0,0 +1,58 @@
+line_buffer API
+===============
+
+The line_buffer library provides a convenient interface for
+mostly-line-oriented input.
+
+Each line is not permitted to exceed 10000 bytes. The provided
+functions are not thread-safe or async-signal-safe, and like
+`fgets()`, they generally do not function correctly if interrupted
+by a signal without SA_RESTART set.
+
+Calling sequence
+----------------
+
+The calling program:
+
+ - specifies a file to read with `buffer_init`
+ - processes input with `buffer_read_line`, `buffer_read_string`,
+ `buffer_skip_bytes`, and `buffer_copy_bytes`
+ - closes the file with `buffer_deinit`, perhaps to start over and
+ read another file.
+
+Before exiting, the caller can use `buffer_reset` to deallocate
+resources for the benefit of profiling tools.
+
+Functions
+---------
+
+`buffer_init`::
+ Open the named file for input. If filename is NULL,
+ start reading from stdin. On failure, returns -1 (with
+ errno indicating the nature of the failure).
+
+`buffer_deinit`::
+ Stop reading from the current file (closing it unless
+ it was stdin). Returns nonzero if `fclose` fails or
+ the error indicator was set.
+
+`buffer_read_line`::
+ Read a line and strip off the trailing newline.
+ On failure or end of file, returns NULL.
+
+`buffer_read_string`::
+ Read `len` characters of input or up to the end of the
+ file, whichever comes first. Returns NULL on error.
+ Returns whatever characters were read (possibly "")
+ for end of file.
+
+`buffer_copy_bytes`::
+ Read `len` bytes of input and dump them to the standard output
+ stream. Returns early for error or end of file.
+
+`buffer_skip_bytes`::
+ Discards `len` bytes from the input stream (stopping early
+ if necessary because of an error or eof).
+
+`buffer_reset`::
+ Deallocates non-static buffers.
--
1.7.2.1.544.ga752d.dirty
next prev parent reply other threads:[~2010-08-09 22:41 UTC|newest]
Thread overview: 79+ messages / expand[flat|nested] mbox.gz Atom feed top
2010-07-15 16:22 [PATCH 0/8] Resurrect rr/svn-export Ramkumar Ramachandra
2010-07-15 16:22 ` [PATCH 1/8] Export parse_date_basic() to convert a date string to timestamp Ramkumar Ramachandra
2010-07-15 17:25 ` Jonathan Nieder
2010-07-15 22:54 ` Junio C Hamano
2010-07-15 16:22 ` [PATCH 2/8] Introduce vcs-svn lib Ramkumar Ramachandra
2010-07-15 17:46 ` Jonathan Nieder
2010-07-15 19:15 ` Ramkumar Ramachandra
2010-07-15 16:22 ` [PATCH 3/8] Add memory pool library Ramkumar Ramachandra
2010-07-15 18:57 ` Jonathan Nieder
2010-07-15 19:12 ` Ramkumar Ramachandra
2010-07-15 16:23 ` [PATCH 4/8] Add treap implementation Ramkumar Ramachandra
2010-07-15 19:09 ` Jonathan Nieder
2010-07-15 19:18 ` Ramkumar Ramachandra
2010-07-15 16:23 ` [PATCH 5/8] Add string-specific memory pool Ramkumar Ramachandra
2010-07-15 16:23 ` [PATCH 6/8] Add stream helper library Ramkumar Ramachandra
2010-07-15 19:19 ` Jonathan Nieder
2010-07-15 16:23 ` [PATCH 7/8] Add infrastructure to write revisions in fast-export format Ramkumar Ramachandra
2010-07-15 19:28 ` Jonathan Nieder
2010-07-15 16:23 ` [PATCH 8/8] Add SVN dump parser Ramkumar Ramachandra
2010-07-15 19:52 ` Jonathan Nieder
2010-07-15 20:04 ` Jonathan Nieder
2010-07-16 10:13 ` [PATCH 0/8] Resurrect rr/svn-export Jonathan Nieder
2010-07-16 10:16 ` [PATCH 3/9] Add memory pool library Jonathan Nieder
2010-07-16 10:23 ` [PATCH 4/9] Add treap implementation Jonathan Nieder
2010-07-16 18:26 ` Jonathan Nieder
2010-08-09 21:57 ` [PATCH 0/10] rr/svn-export reroll Jonathan Nieder
2010-08-09 22:01 ` [PATCH 01/10] Export parse_date_basic() to convert a date string to timestamp Jonathan Nieder
2010-08-09 22:04 ` [PATCH 02/10] Introduce vcs-svn lib Jonathan Nieder
2010-08-09 22:11 ` [PATCH 03/10] Add memory pool library Jonathan Nieder
2010-08-09 22:17 ` [PATCH 04/10] Add treap implementation Jonathan Nieder
2010-08-12 17:22 ` Junio C Hamano
2010-08-12 22:02 ` Jonathan Nieder
2010-08-12 22:11 ` Jonathan Nieder
2010-08-12 22:44 ` Junio C Hamano
2010-08-09 22:34 ` [PATCH 05/10] Add string-specific memory pool Jonathan Nieder
2010-08-12 17:22 ` Junio C Hamano
2010-08-12 21:30 ` Jonathan Nieder
2010-08-09 22:39 ` Jonathan Nieder [this message]
2010-08-09 22:48 ` [PATCH 07/10] Infrastructure to write revisions in fast-export format Jonathan Nieder
2010-08-09 22:55 ` [PATCH 08/10] SVN dump parser Jonathan Nieder
2010-08-12 17:22 ` Junio C Hamano
2010-08-09 22:55 ` PATCH 09/10] Update svn-fe manual Jonathan Nieder
2010-08-09 22:58 ` [PATCH 10/10] svn-fe manual: Clarify warning about deltas in dump files Jonathan Nieder
2010-08-10 12:53 ` [PATCH 0/10] rr/svn-export reroll Ramkumar Ramachandra
2010-08-11 1:53 ` Jonathan Nieder
2010-10-11 2:34 ` [PATCH/WIP 00/16] svn delta applier Jonathan Nieder
2010-10-11 2:37 ` [PATCH 01/16] vcs-svn: Eliminate global byte_buffer[] array Jonathan Nieder
2010-10-11 2:39 ` [PATCH 03/16] vcs-svn: Collect line_buffer data in a struct Jonathan Nieder
2010-10-11 2:41 ` [PATCH 04/16] vcs-svn: Teach line_buffer to handle multiple input files Jonathan Nieder
2010-10-11 2:44 ` [PATCH 05/16] vcs-svn: Make buffer_skip_bytes() report partial reads Jonathan Nieder
2010-10-11 2:46 ` [PATCH 06/16] vcs-svn: Improve support for reading large files Jonathan Nieder
2010-10-11 2:47 ` [PATCH 07/16] vcs-svn: Add binary-safe read() function Jonathan Nieder
2010-10-11 2:47 ` [PATCH 08/16] vcs-svn: Let callers peek ahead to find stream end Jonathan Nieder
2010-10-11 2:51 ` [PATCH 09/16] vcs-svn: Allow input errors to be detected early Jonathan Nieder
2010-10-11 2:52 ` [PATCH 10/16] vcs-svn: Allow character-oriented input Jonathan Nieder
2010-10-11 2:53 ` [PATCH 11/16] vcs-svn: Add code to maintain a sliding view of a file Jonathan Nieder
2010-10-11 2:55 ` [PATCH 12/16] vcs-svn: Learn to parse variable-length integers Jonathan Nieder
2010-10-11 2:58 ` [PATCH 13/16] vcs-svn: Learn to check for SVN\0 magic Jonathan Nieder
2010-10-11 2:59 ` [PATCH 14/16] compat: helper for detecting unsigned overflow Jonathan Nieder
2010-10-11 3:00 ` [PATCH 15/16] t9010 (svn-fe): Eliminate dependency on svn perl bindings Jonathan Nieder
2010-10-11 3:11 ` [PATCH 02/16] vcs-svn: Replace buffer_read_string() memory pool with a strbuf Jonathan Nieder
2010-10-11 4:01 ` [PATCH/RFC 16'/16] vcs-svn: Add svn delta parser Jonathan Nieder
2010-10-13 9:17 ` [PATCH/RFC 0/11] Building up the " Jonathan Nieder
2010-10-13 9:19 ` [PATCH 01/11] fixup! vcs-svn: Learn to parse variable-length integers Jonathan Nieder
2010-10-13 9:21 ` [PATCH 02/11] vcs-svn: Skeleton of an svn delta parser Jonathan Nieder
2010-10-13 9:30 ` [PATCH 03/11] vcs-svn: Read the preimage while applying deltas Jonathan Nieder
2010-10-14 21:45 ` Sam Vilain
2010-10-14 23:40 ` Jonathan Nieder
2010-10-13 9:35 ` [PATCH 04/11] vcs-svn: Read inline data from deltas Jonathan Nieder
2010-10-13 9:38 ` [PATCH 05/11] vcs-svn: Read instructions " Jonathan Nieder
2010-10-13 9:39 ` [PATCH 06/11] vcs-svn: Implement copyfrom_data delta instruction Jonathan Nieder
2010-10-13 9:41 ` [PATCH 07/11] vcs-svn: Check declared number of output bytes Jonathan Nieder
2010-10-13 9:48 ` [PATCH 08/11] vcs-svn: Reject deltas that do not consume all inline data Jonathan Nieder
2010-10-13 9:50 ` [PATCH 09/11] vcs-svn: Let deltas use data from postimage Jonathan Nieder
2010-10-13 9:53 ` [PATCH 10/11] vcs-svn: Reject deltas that read past end of preimage Jonathan Nieder
2010-10-13 9:58 ` [PATCH 11/11] vcs-svn: Allow deltas to copy from preimage Jonathan Nieder
2010-10-13 10:00 ` Jonathan Nieder
2010-10-18 17:00 ` [PATCH/RFC 0/11] Building up the delta parser Ramkumar Ramachandra
2010-10-18 17:03 ` Jonathan Nieder
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
List information: http://vger.kernel.org/majordomo-info.html
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20100809223943.GB4429@burratino \
--to=jrnieder@gmail.com \
--cc=artagnon@gmail.com \
--cc=david.barr@cordelta.com \
--cc=git@vger.kernel.org \
--cc=gitster@pobox.com \
--cc=srabbelier@gmail.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
Code repositories for project(s) associated with this public inbox
https://80x24.org/mirrors/git.git
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for read-only IMAP folder(s) and NNTP newsgroup(s).