Commit e72cb769f6b8c11344463a9784fd4d32ded4a685
2017-07-14T14:37:07
parse: implement `git_parse_peek` Some code parts need to inspect the next few bytes without actually consuming it yet, for example to examine what content it has to expect next. Create a new function `git_parse_peek` which returns the next byte without modifying the parsing context and use it at multiple call sites.
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124
diff --git a/src/parse.c b/src/parse.c
index 57da1c3..c1bd213 100644
--- a/src/parse.c
+++ b/src/parse.c
@@ -94,3 +94,25 @@ int git_parse_advance_digit(int64_t *out, git_parse_ctx *ctx, int base)
git_parse_advance_chars(ctx, (end - ctx->line));
return 0;
}
+
+int git_parse_peek(char *out, git_parse_ctx *ctx, int flags)
+{
+ size_t remain = ctx->line_len;
+ const char *ptr = ctx->line;
+
+ while (remain) {
+ char c = *ptr;
+
+ if ((flags & GIT_PARSE_PEEK_SKIP_WHITESPACE) &&
+ git__isspace(c)) {
+ remain--;
+ ptr++;
+ continue;
+ }
+
+ *out = c;
+ return 0;
+ }
+
+ return -1;
+}
diff --git a/src/parse.h b/src/parse.h
index 8112eae..419014e 100644
--- a/src/parse.h
+++ b/src/parse.h
@@ -48,3 +48,9 @@ int git_parse_advance_expected(
int git_parse_advance_ws(git_parse_ctx *ctx);
int git_parse_advance_nl(git_parse_ctx *ctx);
int git_parse_advance_digit(int64_t *out, git_parse_ctx *ctx, int base);
+
+enum GIT_PARSE_PEEK_FLAGS {
+ GIT_PARSE_PEEK_SKIP_WHITESPACE = (1 << 0)
+};
+
+int git_parse_peek(char *out, git_parse_ctx *ctx, int flags);
diff --git a/src/patch_parse.c b/src/patch_parse.c
index 735b889..8b0a5d3 100644
--- a/src/patch_parse.c
+++ b/src/patch_parse.c
@@ -142,6 +142,8 @@ static int parse_header_oid(
static int parse_header_git_index(
git_patch_parsed *patch, git_patch_parse_ctx *ctx)
{
+ char c;
+
if (parse_header_oid(&patch->base.delta->old_file.id,
&patch->base.delta->old_file.id_abbrev, ctx) < 0 ||
git_parse_advance_expected_str(&ctx->parse_ctx, "..") < 0 ||
@@ -149,7 +151,7 @@ static int parse_header_git_index(
&patch->base.delta->new_file.id_abbrev, ctx) < 0)
return -1;
- if (ctx->parse_ctx.line_len > 0 && ctx->parse_ctx.line[0] == ' ') {
+ if (git_parse_peek(&c, &ctx->parse_ctx, 0) == 0 && c == ' ') {
uint16_t mode;
git_parse_advance_chars(&ctx->parse_ctx, 1);
@@ -458,6 +460,7 @@ static int parse_hunk_header(
git_patch_parse_ctx *ctx)
{
const char *header_start = ctx->parse_ctx.line;
+ char c;
hunk->hunk.old_lines = 1;
hunk->hunk.new_lines = 1;
@@ -466,7 +469,7 @@ static int parse_hunk_header(
parse_int(&hunk->hunk.old_start, ctx) < 0)
goto fail;
- if (ctx->parse_ctx.line_len > 0 && ctx->parse_ctx.line[0] == ',') {
+ if (git_parse_peek(&c, &ctx->parse_ctx, 0) == 0 && c == ',') {
if (git_parse_advance_expected_str(&ctx->parse_ctx, ",") < 0 ||
parse_int(&hunk->hunk.old_lines, ctx) < 0)
goto fail;
@@ -476,7 +479,7 @@ static int parse_hunk_header(
parse_int(&hunk->hunk.new_start, ctx) < 0)
goto fail;
- if (ctx->parse_ctx.line_len > 0 && ctx->parse_ctx.line[0] == ',') {
+ if (git_parse_peek(&c, &ctx->parse_ctx, 0) == 0 && c == ',') {
if (git_parse_advance_expected_str(&ctx->parse_ctx, ",") < 0 ||
parse_int(&hunk->hunk.new_lines, ctx) < 0)
goto fail;
@@ -523,6 +526,7 @@ static int parse_hunk_body(
!git_parse_ctx_contains_s(&ctx->parse_ctx, "@@ -");
git_parse_advance_line(&ctx->parse_ctx)) {
+ char c;
int origin;
int prefix = 1;
@@ -532,7 +536,9 @@ static int parse_hunk_body(
goto done;
}
- switch (ctx->parse_ctx.line[0]) {
+ git_parse_peek(&c, &ctx->parse_ctx, 0);
+
+ switch (c) {
case '\n':
prefix = 0;
@@ -683,9 +689,11 @@ static int parse_patch_binary_side(
}
while (ctx->parse_ctx.line_len) {
- char c = ctx->parse_ctx.line[0];
+ char c;
size_t encoded_len, decoded_len = 0, decoded_orig = decoded.size;
+ git_parse_peek(&c, &ctx->parse_ctx, 0);
+
if (c == '\n')
break;
else if (c >= 'A' && c <= 'Z')