common : move string_remove_suffix from quantize and imatrix

Co-authored-by: Sigbjørn Skjæret <[email protected]>

Author: compilade

common/common.cpp

@@ -448,6 +448,15 @@ void string_replace_all(std::string & s, const std::string & search, const std::
 bool string_ends_with(const std::string_view & str, const std::string_view & suffix) {
     return str.size() >= suffix.size() && str.compare(str.size()-suffix.size(), suffix.size(), suffix) == 0;
 }
+
+bool string_remove_suffix(std::string & str, const std::string_view & suffix) {
+    bool has_suffix = string_ends_with(str, suffix);
+    if (has_suffix) {
+        str = str.substr(0, str.size() - suffix.size());
+    }
+    return has_suffix;
+}
+
 size_t string_find_partial_stop(const std::string_view & str, const std::string_view & stop) {
     if (!str.empty() && !stop.empty()) {
         const char text_last_char = str.back();

common/common.h

@@ -518,6 +518,7 @@ static bool string_starts_with(const std::string & str,
 
 // While we wait for C++20's std::string::ends_with...
 bool string_ends_with(const std::string_view & str, const std::string_view & suffix);
+bool string_remove_suffix(std::string & str, const std::string_view & suffix);
 size_t string_find_partial_stop(const std::string_view & str, const std::string_view & stop);
 
 bool string_parse_kv_override(const char * data, std::vector<llama_model_kv_override> & overrides);

tools/imatrix/imatrix.cpp

@@ -31,18 +31,6 @@ static void print_usage(int, char ** argv) {
     LOG("\n");
 }
 
-static bool str_has_suffix(const std::string & str, const std::string & suffix) {
-    return str.size() >= suffix.size() && str.compare(str.size() - suffix.size(), str.size(), suffix) == 0;
-}
-
-static bool str_remove_suffix(std::string & str, const std::string & suffix) {
-    bool has_suffix = str_has_suffix(str, suffix);
-    if (has_suffix) {
-        str = str.substr(0, str.size() - suffix.size());
-    }
-    return has_suffix;
-}
-
 static const char * const LLM_KV_IMATRIX_DATASETS    = "imatrix.datasets";
 static const char * const LLM_KV_IMATRIX_CHUNK_COUNT = "imatrix.chunk_count";
 static const char * const LLM_KV_IMATRIX_CHUNK_SIZE  = "imatrix.chunk_size";
@@ -362,7 +350,7 @@ void IMatrixCollector::save_imatrix(int32_t n_chunk) const {
     auto fname = m_params.out_file;
 
     // TODO: use the new format by default also for .imatrix
-    if (!str_has_suffix(fname, ".gguf")) {
+    if (!string_ends_with(fname, ".gguf")) {
         this->save_imatrix_legacy(n_chunk);
         return;
     }
@@ -584,10 +572,10 @@ bool IMatrixCollector::load_imatrix(const char * file_name) {
 
         if (name.empty()) { continue; }
 
-        if (str_remove_suffix(name, in_sum2_suffix)) {
+        if (string_remove_suffix(name, in_sum2_suffix)) {
             // in_sum2
             sums_counts_for[std::move(name)].first = cur;
-        } else if (str_remove_suffix(name, counts_suffix)) {
+        } else if (string_remove_suffix(name, counts_suffix)) {
             // counts
             sums_counts_for[std::move(name)].second = cur;
         } else {

tools/quantize/quantize.cpp

@@ -147,15 +147,6 @@ static void usage(const char * executable) {
     exit(1);
 }
 
-// TODO: share with implementation in imatrix.cpp
-static bool str_remove_suffix(std::string & str, const std::string & suffix) {
-    bool has_suffix = str.size() >= suffix.size() && str.compare(str.size() - suffix.size(), str.size(), suffix) == 0;
-    if (has_suffix) {
-        str = str.substr(0, str.size() - suffix.size());
-    }
-    return has_suffix;
-}
-
 static int load_legacy_imatrix(const std::string & imatrix_file, std::vector<std::string> & imatrix_datasets, std::unordered_map<std::string, std::vector<float>> & imatrix_data) {
     std::ifstream in(imatrix_file.c_str(), std::ios::binary);
     if (!in) {
@@ -265,10 +256,10 @@ static int load_imatrix(const std::string & imatrix_file, std::vector<std::strin
 
         if (name.empty()) { continue; }
 
-        if (str_remove_suffix(name, sums_suffix)) {
+        if (string_remove_suffix(name, sums_suffix)) {
             // in_sum2
             sums_counts_for[std::move(name)].first = cur;
-        } else if (str_remove_suffix(name, counts_suffix)) {
+        } else if (string_remove_suffix(name, counts_suffix)) {
             // counts
             sums_counts_for[std::move(name)].second = cur;
         } else {