Add StreamReader and rebuild Parser/LineParser/IMFHeader/IMFBoundary on it

Introduces StreamReader to accumulate socket data delivered in arbitrary
chunks into one buffer, so a Parser can build an object (a line, a header
block, a MIME boundary) that spans any number of packets without losing
its place. Parser is redesigned around this: no longer inherits MString
(was redundant with its own buffer member), takes a StreamReader&, and
drives a resumable COMPLETE/INCOMPLETE/DATA_AVAIL state-machine protocol
via doParse(). LineParser, IMFHeader, and IMFBoundary are rewritten as
real, working resumable parsers against the shared buffer instead of the
previous non-compiling stubs (mismatched constructors/return types, a
syntax error, checkParse() never implemented).

IMFFormData is left as the stub it already was, just restored to
compiling against the new IMFHeader signature - fully wiring it up needs
IMFMultipart/IMFText migrated to StreamReader too, out of scope here.

Verified with real runtime tests (not just compilation) covering data
split mid-line, mid-CRLF, mid-header-fold, and mid-boundary-marker across
separate feed() calls, plus StreamReader::compact(). Along the way fixed
a header-value bug (space after ':' wasn't skipped) and a double
cursor-offset subtraction bug in two places caused by forgetting that
ZString::getLength() is already cursor-relative, not the raw buffer size.

Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
This commit is contained in:
Brad ArantandClaude Sonnet 5 committed 2026-08-23 14:25:58 -07:00
1 parent 94d4a30e88
commit a033cc6718
13 files changed
+443 -136

No files matched your search

+65 -6
View File
@@ -1,14 +1,73 @@
#include <iostream>
#include "../MString.h"
#include <cassert>
#include <cstring>
#include "../StreamReader.h"
#include "../LineParser.h"
#include "../IMFHeader.h"
#include "../IMFBoundary.h"
int main(int argc, char **argv) {
using namespace coreutils;
coreutils::LineParser line(0);
Parse.Status status = line.doParse();
static int checks = 0;
#define CHECK(cond) do { checks++; if(!(cond)) { std::cerr << "FAIL line " << __LINE__ << ": " #cond << std::endl; return 1; } } while(0)
void feedStr(StreamReader &r, const char *s) {
ZString z((char *)s, strlen(s));
r.feed(z);
}
// The whole point of StreamReader/Parser: a "line" (or header, or boundary)
// can arrive split across any number of socket packets, and parsing must
// resume cleanly from wherever it left off once more data shows up.
int test_lineparser_split_across_feeds() {
StreamReader reader;
feedStr(reader, "partial li");
LineParser lp(reader);
CHECK(lp.doParse() == Parser::Status::INCOMPLETE);
feedStr(reader, "ne\r\n");
CHECK(lp.doParse() == Parser::Status::COMPLETE);
ZString line = lp.getLine();
CHECK(line.getLength() == 12);
CHECK(strncmp(line.getData(), "partial line", 12) == 0);
return 0;
}
int test_imfheader_folding_and_split_feeds() {
StreamReader reader;
IMFHeader header(reader);
feedStr(reader, "Subject: line one\r\n ");
CHECK(header.doParse() == Parser::Status::INCOMPLETE);
feedStr(reader, "line two\r\n\r\n");
CHECK(header.doParse() == Parser::Status::COMPLETE);
auto &fields = header.getHeaders();
CHECK(fields.size() == 1);
MString subj = fields[MString("Subject")];
CHECK(subj.getLength() == 17);
CHECK(strncmp(subj.getData(), "line one line two", subj.getLength()) == 0);
return 0;
}
int test_imfboundary_split_across_feeds() {
ZString b((char *)"XYZ", 3);
StreamReader reader;
IMFBoundary bound(reader, b);
feedStr(reader, "\r\n--X");
CHECK(bound.doParse() == Parser::Status::INCOMPLETE);
feedStr(reader, "YZ--");
CHECK(bound.doParse() == Parser::Status::COMPLETE);
CHECK(bound.isLast() == true);
return 0;
}
int main() {
int rc = 0;
rc |= test_lineparser_split_across_feeds();
rc |= test_imfheader_folding_and_split_feeds();
rc |= test_imfboundary_split_across_feeds();
if (rc == 0)
std::cout << "ALL " << checks << " CHECKS PASSED" << std::endl;
else
std::cout << "SOME CHECKS FAILED (see above)" << std::endl;
return rc;
}