From 32d61d7c48b7cf0eb7445fb410e339bbcadd1d61 Mon Sep 17 00:00:00 2001
From: Simon Tatham <anakin@pobox.com>
Date: Mon, 6 Jan 2020 19:55:41 +0000
Subject: [PATCH] Add some more marshalling functions, for file parsing.

There are new functions here to get the next contiguous string of
characters from a given set (like strspn/strcspn, only for
BinarySource, and returning a ptrlen of what they skipped over). Also
we can get a line of text with the trailing newline chomped off.
Finally, I've provided a function to rewind a BinarySource to a
previous position with error checking.
---
 marshal.c | 58 +++++++++++++++++++++++++++++++++++++++++++++++++++++++
 marshal.h | 15 ++++++++++++++
 2 files changed, 73 insertions(+)

diff --git a/marshal.c b/marshal.c
index a9b1074a..fd287aa1 100644
--- a/marshal.c
+++ b/marshal.c
@@ -218,6 +218,53 @@ const char *BinarySource_get_asciz(BinarySource *src)
     return start;
 }
 
+static ptrlen BinarySource_get_chars_internal(
+    BinarySource *src, const char *set, bool include)
+{
+    const char *start = here;
+    while (avail(1)) {
+        bool present = NULL != strchr(set, *(const char *)consume(0));
+        if (present != include)
+            break;
+        consume(1);
+    }
+    const char *end = here;
+    return make_ptrlen(start, end - start);
+}
+
+ptrlen BinarySource_get_chars(BinarySource *src, const char *include_set)
+{
+    return BinarySource_get_chars_internal(src, include_set, true);
+}
+
+ptrlen BinarySource_get_nonchars(BinarySource *src, const char *exclude_set)
+{
+    return BinarySource_get_chars_internal(src, exclude_set, false);
+}
+
+ptrlen BinarySource_get_chomped_line(BinarySource *src)
+{
+    const char *start, *end;
+
+    if (src->err)
+        return make_ptrlen(here, 0);
+
+    start = here;
+    end = memchr(start, '\n', src->len - src->pos);
+    if (end)
+        advance(end + 1 - start);
+    else
+        advance(src->len - src->pos);
+    end = here;
+
+    if (end > start && end[-1] == '\n')
+        end--;
+    if (end > start && end[-1] == '\r')
+        end--;
+
+    return make_ptrlen(start, end - start);
+}
+
 ptrlen BinarySource_get_pstring(BinarySource *src)
 {
     const unsigned char *ucp;
@@ -235,6 +282,17 @@ ptrlen BinarySource_get_pstring(BinarySource *src)
     return make_ptrlen(consume(len), len);
 }
 
+void BinarySource_REWIND_TO__(BinarySource *src, size_t pos)
+{
+    if (pos <= src->len) {
+        src->pos = pos;
+        src->err = BSE_NO_ERROR;    /* clear any existing error */
+    } else {
+        src->pos = src->len;
+        src->err = BSE_OUT_OF_DATA; /* new error if we rewind out of range */
+    }
+}
+
 static void stdio_sink_write(BinarySink *bs, const void *data, size_t len)
 {
     stdio_sink *sink = BinarySink_DOWNCAST(bs, stdio_sink);
diff --git a/marshal.h b/marshal.h
index bc020a8d..108d8aeb 100644
--- a/marshal.h
+++ b/marshal.h
@@ -255,6 +255,10 @@ static inline void BinarySource_INIT__(BinarySource *src, ptrlen data)
               (object)->binarysource_)
 #define BinarySource_COPIED(obj) \
     ((obj)->binarysource_->binarysource_ = (obj)->binarysource_)
+#define BinarySource_REWIND_TO(src, pos) \
+    BinarySource_REWIND_TO__((src)->binarysource_, pos)
+#define BinarySource_REWIND(src) \
+    BinarySource_REWIND_TO__((src)->binarysource_, 0)
 
 #define get_data(src, len) \
     BinarySource_get_data(BinarySource_UPCAST(src), len)
@@ -272,6 +276,12 @@ static inline void BinarySource_INIT__(BinarySource *src, ptrlen data)
     BinarySource_get_string(BinarySource_UPCAST(src))
 #define get_asciz(src) \
     BinarySource_get_asciz(BinarySource_UPCAST(src))
+#define get_chars(src, include) \
+    BinarySource_get_chars(BinarySource_UPCAST(src), include)
+#define get_nonchars(src, exclude) \
+    BinarySource_get_nonchars(BinarySource_UPCAST(src), exclude)
+#define get_chomped_line(src) \
+    BinarySource_get_chomped_line(BinarySource_UPCAST(src))
 #define get_pstring(src) \
     BinarySource_get_pstring(BinarySource_UPCAST(src))
 #define get_mp_ssh1(src) \
@@ -301,10 +311,15 @@ unsigned long BinarySource_get_uint32(BinarySource *);
 uint64_t BinarySource_get_uint64(BinarySource *);
 ptrlen BinarySource_get_string(BinarySource *);
 const char *BinarySource_get_asciz(BinarySource *);
+ptrlen BinarySource_get_chars(BinarySource *, const char *include_set);
+ptrlen BinarySource_get_nonchars(BinarySource *, const char *exclude_set);
+ptrlen BinarySource_get_chomped_line(BinarySource *);
 ptrlen BinarySource_get_pstring(BinarySource *);
 mp_int *BinarySource_get_mp_ssh1(BinarySource *src);
 mp_int *BinarySource_get_mp_ssh2(BinarySource *src);
 
+void BinarySource_REWIND_TO__(BinarySource *src, size_t pos);
+
 /*
  * A couple of useful standard BinarySink implementations, which live
  * as sensibly here as anywhere else: one that makes a BinarySink