288 lines
12 KiB
C++
288 lines
12 KiB
C++
#include "capture_paths.h"
|
|
|
|
#include <cassert>
|
|
#include <cctype>
|
|
#include <cstdint>
|
|
#include <cstdio>
|
|
#include <cstring> // std::memcmp
|
|
#include <filesystem>
|
|
#include <vector>
|
|
|
|
namespace reasampler {
|
|
|
|
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());
|
|
}
|
|
|
|
std::string normalizeSlashes(const std::string& path) {
|
|
std::string out = path;
|
|
for (char& c : out) {
|
|
if (c == '\\') c = '/';
|
|
}
|
|
// Strip a single trailing slash so joins do not double up. Preserve a lone
|
|
// "/" (root) — stripping it would turn root into empty.
|
|
if (out.size() > 1 && out.back() == '/') {
|
|
out.pop_back();
|
|
}
|
|
#ifdef _WIN32
|
|
// Windows paths are case-insensitive. Fold to lowercase so that two paths
|
|
// that differ only in drive-letter or component casing compare equal (e.g.
|
|
// "C:/Foo/BAR.wav" == "c:/foo/bar.wav"). On macOS/Linux, exact case is
|
|
// preserved (the filesystem is case-sensitive; folding would be wrong).
|
|
for (char& c : out) c = static_cast<char>(std::tolower(static_cast<unsigned char>(c)));
|
|
#endif
|
|
return out;
|
|
}
|
|
|
|
std::string sanitizeStem(const std::string& baseName) {
|
|
std::string out;
|
|
out.reserve(baseName.size());
|
|
for (unsigned char c : baseName) {
|
|
const bool keep = (c >= 'A' && c <= 'Z') || (c >= 'a' && c <= 'z') ||
|
|
(c >= '0' && c <= '9') || c == '.' || c == '_' ||
|
|
c == '-';
|
|
out.push_back(keep ? static_cast<char>(c) : '_');
|
|
}
|
|
// Collapse to a stable default if nothing usable survived (e.g. all spaces).
|
|
// A stem of only separators ('.', '_', '-') is also unhelpful as a name.
|
|
bool hasAlnum = false;
|
|
for (unsigned char c : out) {
|
|
if ((c >= 'A' && c <= 'Z') || (c >= 'a' && c <= 'z') ||
|
|
(c >= '0' && c <= '9')) {
|
|
hasAlnum = true;
|
|
break;
|
|
}
|
|
}
|
|
if (out.empty() || !hasAlnum) {
|
|
return "capture";
|
|
}
|
|
return out;
|
|
}
|
|
|
|
BankPaths deriveBankPaths(const std::string& projectDir,
|
|
const std::string& baseName,
|
|
const std::string& uniqueTag) {
|
|
const std::string dir = normalizeSlashes(projectDir);
|
|
|
|
std::string stem = sanitizeStem(baseName);
|
|
if (!uniqueTag.empty()) {
|
|
stem += "_" + sanitizeStem(uniqueTag);
|
|
}
|
|
const std::string fileName = stem + ".wav";
|
|
|
|
// Precondition: the capture shell must resolve a non-empty project directory
|
|
// before calling this function. An empty projectDir would produce a bare
|
|
// relative "reasampler_bank" path — the silent default-location fallback this
|
|
// tool explicitly forbids. Assert in debug; leave absoluteDir empty in release
|
|
// so any caller that ignores the precondition fails loudly at the render/stat
|
|
// step rather than silently writing to CWD.
|
|
assert(!dir.empty() && "deriveBankPaths: projectDir must not be empty");
|
|
|
|
BankPaths p;
|
|
p.fileStem = stem; // stem only — REAPER appends extension
|
|
p.fileName = fileName;
|
|
p.relativePath = std::string(kBankSubfolder) + "/" + fileName;
|
|
// absoluteDir intentionally omits a trailing slash (RENDER_FILE wants the
|
|
// directory itself; RENDER_PATTERN supplies the file name separately).
|
|
// Empty when precondition is violated (dir empty) — caller must not proceed.
|
|
p.absoluteDir = dir.empty() ? std::string{}
|
|
: dir + "/" + kBankSubfolder;
|
|
return p;
|
|
}
|
|
|
|
std::string bankRelativeForName(const std::string& fileName) {
|
|
if (fileName.empty()) return {};
|
|
// The SAME expression deriveBankPaths uses for relativePath, kept in one place so
|
|
// the two spellings can never drift (Phase R spelling-consistency invariant).
|
|
return std::string(kBankSubfolder) + "/" + fileName;
|
|
}
|
|
|
|
std::string resolveBankFile(const std::string& projectDir,
|
|
const std::string& relativePath) {
|
|
// No default-location fallback (CLAUDE.md invariant): an empty project dir or
|
|
// relative path yields empty, not a bare relative path resolved against CWD.
|
|
if (projectDir.empty() || relativePath.empty()) {
|
|
return {};
|
|
}
|
|
const std::string dir = normalizeSlashes(projectDir);
|
|
const std::string rel = normalizeSlashes(relativePath);
|
|
if (dir.empty() || rel.empty()) {
|
|
return {};
|
|
}
|
|
return dir + "/" + rel;
|
|
}
|
|
|
|
std::string projectDirOfRpp(const std::string& rppPath) {
|
|
// An unsaved project reports an empty .rpp path; keep it empty so downstream
|
|
// resolution refuses (no default-location fallback). Mirrors persist.cpp's prior
|
|
// projectDirOf exactly: parent_path of the .rpp, then normalizeSlashes.
|
|
if (rppPath.empty()) return {};
|
|
std::string dir = std::filesystem::path(rppPath).parent_path().string();
|
|
return normalizeSlashes(dir);
|
|
}
|
|
|
|
BankRelocation deriveRelocationPlan(const std::string& oldProjectDir,
|
|
const std::string& newProjectDir) {
|
|
BankRelocation r;
|
|
if (oldProjectDir.empty() || newProjectDir.empty()) {
|
|
return r; // needed=false, empty dirs — nothing to relocate
|
|
}
|
|
const std::string oldDir = normalizeSlashes(oldProjectDir);
|
|
const std::string newDir = normalizeSlashes(newProjectDir);
|
|
|
|
r.oldBankDir = oldDir + "/" + kBankSubfolder;
|
|
r.newBankDir = newDir + "/" + kBankSubfolder;
|
|
// A Save (in place) leaves the project dir unchanged — nothing to relocate.
|
|
// Only a Save-As to a different directory needs the bank moved.
|
|
r.needed = (oldDir != newDir);
|
|
return r;
|
|
}
|
|
|
|
ProjectTransition classifyProjectTransition(bool sameProjectObject,
|
|
const std::string& lastGuid,
|
|
const std::string& lastPath,
|
|
const std::string& currentGuid,
|
|
const std::string& currentPath) {
|
|
// 1. The GUID is the identity of record and is checked FIRST. A different
|
|
// stored GUID means a genuinely different project is active — Load ITS index.
|
|
// This catches the regression that pointer-primary classification missed:
|
|
// REAPER RECYCLES ReaProject* addresses across close/open, so a reopened /
|
|
// new project can reuse the previous project's address (sameProjectObject ==
|
|
// true) while carrying a different stored GUID. Deciding on the pointer alone
|
|
// then returned NoOp/SaveAsRelocate and the bank never reloaded. The GUID is
|
|
// immune to address recycling, so it leads. Also covers new/unsaved<->saved
|
|
// transitions (one GUID empty, the other not) and switching between two
|
|
// distinct saved projects.
|
|
if (currentGuid != lastGuid) {
|
|
return ProjectTransition::Load;
|
|
}
|
|
|
|
// From here currentGuid == lastGuid (they are equal; both may be empty for
|
|
// unsaved projects). The pointer now disambiguates the same-GUID case.
|
|
|
|
// 2. Same GUID but a DIFFERENT object is a forked sibling: Save-As copied our
|
|
// GUID onto a distinct project object. Load its (own) index; never relocate.
|
|
// Two unsaved projects (both GUIDs empty, distinct objects) also land here —
|
|
// Load, so switching between them installs the right in-memory state.
|
|
if (!sameProjectObject) {
|
|
return ProjectTransition::Load;
|
|
}
|
|
|
|
// 3. Same object AND same GUID with a NEW path is a genuine Save-As (the object
|
|
// identity is proven and the record identity is unchanged — only the .rpp
|
|
// moved). Also the first save of an unsaved project (both GUIDs empty, old
|
|
// path empty): SaveAsRelocate is safe there because deriveRelocationPlan
|
|
// no-ops on the empty old dir (empty-GUID safety preserved) while poll()
|
|
// mints a GUID.
|
|
if (currentPath != lastPath) {
|
|
return ProjectTransition::SaveAsRelocate;
|
|
}
|
|
|
|
// 4. Same object, same GUID, same path — Save in place / idle tick.
|
|
return ProjectTransition::NoOp;
|
|
}
|
|
|
|
} // namespace reasampler
|