Q-W3: main.cpp → pointers+entry+dispatch via 4 capture hoists; one pure wav_codec RIFF owner; ICaptureBackend deleted; capture_realtime rename + finalize split; shared stampCaptureSample; makeUniqueTag gains monotonic counter (fixes same-second batch collisions). 60/60 green.
This commit is contained in:
@@ -2,119 +2,13 @@
|
||||
|
||||
#include <cassert>
|
||||
#include <cctype>
|
||||
#include <cstdint>
|
||||
#include <cstdio>
|
||||
#include <cstring> // std::memcmp
|
||||
#include <filesystem>
|
||||
#include <vector>
|
||||
|
||||
namespace reasampler::capture {
|
||||
|
||||
std::string hashBytes(const std::uint8_t* data, std::size_t len) {
|
||||
// FNV-1a 64-bit: deterministic, no dependencies, adequate for dedup identity.
|
||||
// Constants from the FNV spec (http://www.isthe.com/chongo/tech/comp/fnv/).
|
||||
constexpr std::uint64_t kOffsetBasis = 14695981039346656037ULL;
|
||||
constexpr std::uint64_t kPrime = 1099511628211ULL;
|
||||
std::uint64_t h = kOffsetBasis;
|
||||
for (std::size_t i = 0; i < len; ++i) {
|
||||
h ^= static_cast<std::uint64_t>(data[i]);
|
||||
h *= kPrime;
|
||||
}
|
||||
// Format as 16-digit lowercase hex (zero-padded) for a fixed-length string.
|
||||
char buf[17];
|
||||
std::snprintf(buf, sizeof(buf), "%016llx",
|
||||
static_cast<unsigned long long>(h));
|
||||
return std::string(buf);
|
||||
}
|
||||
|
||||
std::string hashWavContent(const std::vector<std::uint8_t>& bytes) {
|
||||
// Walk the RIFF/WAVE container and feed only the `fmt ` body and `data` body
|
||||
// through FNV-1a, prefixed with the domain-separation tag byte 'W' (0x57).
|
||||
// Any render-varying metadata chunks (bext, iXML, LIST, SMED, etc.) are skipped.
|
||||
// If the file does not parse as RIFF/WAVE with both fmt and data chunks, fall back
|
||||
// to whole-file hashBytes (no prefix) so an unrecognized file still gets a hash.
|
||||
//
|
||||
// The chunk-walk mirrors wav_trim::parseWavLayout's structure but accumulates
|
||||
// FNV state instead of recording geometry — no second parser, same logic.
|
||||
|
||||
// FNV-1a 64-bit constants (same as hashBytes).
|
||||
constexpr std::uint64_t kOffsetBasis = 14695981039346656037ULL;
|
||||
constexpr std::uint64_t kPrime = 1099511628211ULL;
|
||||
|
||||
// Minimum viable RIFF/WAVE: "RIFF"(4) size(4) "WAVE"(4) = 12 bytes.
|
||||
auto tagEq = [&](std::size_t off, const char* tag) -> bool {
|
||||
return off + 4 <= bytes.size() &&
|
||||
std::memcmp(bytes.data() + off, tag, 4) == 0;
|
||||
};
|
||||
auto readU32LE = [&](std::size_t off) -> std::uint32_t {
|
||||
return static_cast<std::uint32_t>(bytes[off]) |
|
||||
(static_cast<std::uint32_t>(bytes[off + 1]) << 8) |
|
||||
(static_cast<std::uint32_t>(bytes[off + 2]) << 16) |
|
||||
(static_cast<std::uint32_t>(bytes[off + 3]) << 24);
|
||||
};
|
||||
|
||||
bool isWav = bytes.size() >= 12 &&
|
||||
tagEq(0, "RIFF") &&
|
||||
tagEq(8, "WAVE");
|
||||
|
||||
if (isWav) {
|
||||
// Accumulate FNV-1a starting with the domain-separation tag byte 'W'.
|
||||
std::uint64_t h = kOffsetBasis;
|
||||
auto feedByte = [&](std::uint8_t b) {
|
||||
h ^= static_cast<std::uint64_t>(b);
|
||||
h *= kPrime;
|
||||
};
|
||||
|
||||
bool haveFmt = false;
|
||||
bool haveData = false;
|
||||
|
||||
// Domain-separation prefix: 'W' (0x57) distinguishes a content hash from a
|
||||
// whole-file hash of different bytes that happen to be the same length.
|
||||
feedByte(static_cast<std::uint8_t>('W'));
|
||||
|
||||
std::size_t pos = 12;
|
||||
while (pos + 8 <= bytes.size()) {
|
||||
const std::size_t bodyOffset = pos + 8;
|
||||
const std::uint32_t bodySize = readU32LE(pos + 4);
|
||||
|
||||
if (tagEq(pos, "fmt ")) {
|
||||
// Feed the entire fmt body (all fields, including format tag, channels,
|
||||
// sample rate, bits-per-sample — everything that defines the audio format).
|
||||
if (bodyOffset + bodySize <= bytes.size()) {
|
||||
for (std::uint32_t i = 0; i < bodySize; ++i)
|
||||
feedByte(bytes[bodyOffset + i]);
|
||||
haveFmt = true;
|
||||
}
|
||||
} else if (tagEq(pos, "data")) {
|
||||
// Feed the entire PCM payload.
|
||||
if (bodyOffset + bodySize <= bytes.size()) {
|
||||
for (std::uint32_t i = 0; i < bodySize; ++i)
|
||||
feedByte(bytes[bodyOffset + i]);
|
||||
haveData = true;
|
||||
}
|
||||
}
|
||||
// All other chunks (bext, iXML, LIST, SMED, cue, etc.) are skipped.
|
||||
|
||||
// Advance past this chunk's body, honoring RIFF even-byte padding.
|
||||
std::size_t advance = bodySize;
|
||||
if (advance & 1u) ++advance; // RIFF pad byte
|
||||
if (advance > bytes.size() - bodyOffset) break; // overrun guard
|
||||
pos = bodyOffset + advance;
|
||||
}
|
||||
|
||||
if (haveFmt && haveData) {
|
||||
char buf[17];
|
||||
std::snprintf(buf, sizeof(buf), "%016llx",
|
||||
static_cast<unsigned long long>(h));
|
||||
return std::string(buf);
|
||||
}
|
||||
// Falls through to whole-file fallback if chunks were missing/malformed.
|
||||
}
|
||||
|
||||
// Fallback: not a parseable RIFF/WAVE — hash the whole file (same as the old
|
||||
// per-call hashBytes). No prefix tag: identical to hashBytes(data, size).
|
||||
return hashBytes(bytes.data(), bytes.size());
|
||||
}
|
||||
// The content-identity hashes (hashBytes / hashWavContent) moved to wav_codec
|
||||
// (Q-W3, audit §4e) — one pure owner of the RIFF chunk walk, shared with the
|
||||
// layout parse so hashing and decoding cannot desynchronize.
|
||||
|
||||
std::string normalizeSlashes(const std::string& path) {
|
||||
std::string out = path;
|
||||
|
||||
Reference in New Issue
Block a user