local-llm-rn 1.0.0

package/cpp/common/jinja/string.cpp

@@ -0,0 +1,213 @@
+#include "jinja/string.h"
+#include "jinja/value.h"
+
+#include <algorithm>
+#include <functional>
+#include <optional>
+#include <sstream>
+#include <string>
+#include <vector>
+
+namespace jinja {
+
+//
+// string_part
+//
+
+bool string_part::is_uppercase() const {
+    for (char c : val) {
+        if (std::islower(static_cast<unsigned char>(c))) {
+            return false;
+        }
+    }
+    return true;
+}
+
+bool string_part::is_lowercase() const {
+    for (char c : val) {
+        if (std::isupper(static_cast<unsigned char>(c))) {
+            return false;
+        }
+    }
+    return true;
+}
+
+//
+// string
+//
+
+void string::mark_input() {
+    for (auto & part : parts) {
+        part.is_input = true;
+    }
+}
+
+std::string string::str() const {
+    if (parts.size() == 1) {
+        return parts[0].val;
+    }
+    std::ostringstream oss;
+    for (const auto & part : parts) {
+        oss << part.val;
+    }
+    return oss.str();
+}
+
+size_t string::length() const {
+    size_t len = 0;
+    for (const auto & part : parts) {
+        len += part.val.length();
+    }
+    return len;
+}
+
+void string::hash_update(hasher & hash) const noexcept {
+    for (const auto & part : parts) {
+        hash.update(part.val.data(), part.val.length());
+    }
+}
+
+bool string::all_parts_are_input() const {
+    for (const auto & part : parts) {
+        if (!part.is_input) {
+            return false;
+        }
+    }
+    return true;
+}
+
+bool string::is_uppercase() const {
+    for (const auto & part : parts) {
+        if (!part.is_uppercase()) {
+            return false;
+        }
+    }
+    return true;
+}
+
+bool string::is_lowercase() const {
+    for (const auto & part : parts) {
+        if (!part.is_lowercase()) {
+            return false;
+        }
+    }
+    return true;
+}
+
+// mark this string as input if other has ALL parts as input
+void string::mark_input_based_on(const string & other) {
+    if (other.all_parts_are_input()) {
+        for (auto & part : parts) {
+            part.is_input = true;
+        }
+    }
+}
+
+string string::append(const string & other) {
+    for (const auto & part : other.parts) {
+        parts.push_back(part);
+    }
+    return *this;
+}
+
+// in-place transformation
+
+using transform_fn = std::function<std::string(const std::string&)>;
+static string apply_transform(string & self, const transform_fn & fn) {
+    for (auto & part : self.parts) {
+        part.val = fn(part.val);
+    }
+    return self;
+}
+
+string string::uppercase() {
+    return apply_transform(*this, [](const std::string & s) {
+        std::string res = s;
+        std::transform(res.begin(), res.end(), res.begin(), ::toupper);
+        return res;
+    });
+}
+string string::lowercase() {
+    return apply_transform(*this, [](const std::string & s) {
+        std::string res = s;
+        std::transform(res.begin(), res.end(), res.begin(), ::tolower);
+        return res;
+    });
+}
+string string::capitalize() {
+    return apply_transform(*this, [](const std::string & s) {
+        if (s.empty()) return s;
+        std::string res = s;
+        res[0] = ::toupper(static_cast<unsigned char>(res[0]));
+        std::transform(res.begin() + 1, res.end(), res.begin() + 1, ::tolower);
+        return res;
+    });
+}
+string string::titlecase() {
+    return apply_transform(*this, [](const std::string & s) {
+        std::string res = s;
+        bool capitalize_next = true;
+        for (char &c : res) {
+            if (isspace(static_cast<unsigned char>(c))) {
+                capitalize_next = true;
+            } else if (capitalize_next) {
+                c = ::toupper(static_cast<unsigned char>(c));
+                capitalize_next = false;
+            } else {
+                c = ::tolower(static_cast<unsigned char>(c));
+            }
+        }
+        return res;
+    });
+}
+string string::strip(bool left, bool right, std::optional<const std::string_view> chars) {
+    static auto strip_part = [](const std::string & s, bool left, bool right, std::optional<const std::string_view> chars) -> std::string {
+        size_t start = 0;
+        size_t end = s.length();
+        auto match_char = [&chars](unsigned char c) -> bool {
+            return chars ? (*chars).find(c) != std::string::npos : isspace(c);
+        };
+        if (left) {
+            while (start < end && match_char(static_cast<unsigned char>(s[start]))) {
+                ++start;
+            }
+        }
+        if (right) {
+            while (end > start && match_char(static_cast<unsigned char>(s[end - 1]))) {
+                --end;
+            }
+        }
+        return s.substr(start, end - start);
+    };
+    if (parts.empty()) {
+        return *this;
+    }
+    if (left) {
+        for (size_t i = 0; i < parts.size(); ++i) {
+            parts[i].val = strip_part(parts[i].val, true, false, chars);
+            if (parts[i].val.empty()) {
+                // remove empty part
+                parts.erase(parts.begin() + i);
+                --i;
+                continue;
+            } else {
+                break;
+            }
+        }
+    }
+    if (right) {
+        for (size_t i = parts.size(); i-- > 0;) {
+            parts[i].val = strip_part(parts[i].val, false, true, chars);
+            if (parts[i].val.empty()) {
+                // remove empty part
+                parts.erase(parts.begin() + i);
+                continue;
+            } else {
+                break;
+            }
+        }
+    }
+    return *this;
+}
+
+} // namespace jinja

package/cpp/common/jinja/string.h

@@ -0,0 +1,61 @@
+#pragma once
+
+#include <optional>
+#include <string>
+#include <vector>
+
+#include "utils.h"
+
+namespace jinja {
+
+// allow differentiate between user input strings and template strings
+// transformations should handle this information as follows:
+// - one-to-one (e.g., uppercase, lowercase): preserve is_input flag
+// - one-to-many (e.g., strip): if input string is marked as is_input, all resulting parts should be marked as is_input
+// - many-to-one (e.g., concat): if ALL input parts are marked as is_input, resulting part should be marked as is_input
+struct string_part {
+    bool is_input = false; // may skip parsing special tokens if true
+    std::string val;
+
+    bool is_uppercase() const;
+    bool is_lowercase() const;
+};
+
+struct string {
+    std::vector<string_part> parts;
+    string() = default;
+    string(const std::string & v, bool user_input = false) {
+        parts.push_back({user_input, v});
+    }
+    string(int v) {
+        parts.push_back({false, std::to_string(v)});
+    }
+    string(double v) {
+        parts.push_back({false, std::to_string(v)});
+    }
+
+    // mark all parts as user input
+    void mark_input();
+
+    std::string str() const;
+    size_t length() const;
+    void hash_update(hasher & hash) const noexcept;
+    bool all_parts_are_input() const;
+    bool is_uppercase() const;
+    bool is_lowercase() const;
+
+    // mark this string as input if other has ALL parts as input
+    void mark_input_based_on(const string & other);
+
+    string append(const string & other);
+
+    // in-place transformations
+
+    string uppercase();
+    string lowercase();
+    string capitalize();
+    string titlecase();
+    string strip(bool left, bool right, std::optional<const std::string_view> chars = std::nullopt);
+};
+
+} // namespace jinja

package/cpp/common/jinja/utils.h

@@ -0,0 +1,149 @@
+#pragma once
+
+#include <string>
+#include <sstream>
+#include <algorithm>
+#include <cstdint>
+#include <cstring>
+
+namespace jinja {
+
+static void string_replace_all(std::string & s, const std::string & search, const std::string & replace) {
+    if (search.empty()) {
+        return;
+    }
+    std::string builder;
+    builder.reserve(s.length());
+    size_t pos = 0;
+    size_t last_pos = 0;
+    while ((pos = s.find(search, last_pos)) != std::string::npos) {
+        builder.append(s, last_pos, pos - last_pos);
+        builder.append(replace);
+        last_pos = pos + search.length();
+    }
+    builder.append(s, last_pos, std::string::npos);
+    s = std::move(builder);
+}
+
+// for displaying source code around error position
+static std::string peak_source(const std::string & source, size_t pos, size_t max_peak_chars = 40) {
+    if (source.empty()) {
+        return "(no source available)";
+    }
+    std::string output;
+    size_t start = (pos >= max_peak_chars) ? (pos - max_peak_chars) : 0;
+    size_t end = std::min(pos + max_peak_chars, source.length());
+    std::string substr = source.substr(start, end - start);
+    string_replace_all(substr, "\n", "↵");
+    output += "..." + substr + "...\n";
+    std::string spaces(pos - start + 3, ' ');
+    output += spaces + "^";
+    return output;
+}
+
+static std::string fmt_error_with_source(const std::string & tag, const std::string & msg, const std::string & source, size_t pos) {
+    std::ostringstream oss;
+    oss << tag << ": " << msg << "\n";
+    oss << peak_source(source, pos);
+    return oss.str();
+}
+
+// Note: this is a simple hasher, not cryptographically secure, just for hash table usage
+struct hasher {
+    static constexpr auto size_t_digits = sizeof(size_t) * 8;
+    static constexpr size_t prime = size_t_digits == 64 ? 0x100000001b3 : 0x01000193;
+    static constexpr size_t seed = size_t_digits == 64 ? 0xcbf29ce484222325 : 0x811c9dc5;
+    static constexpr auto block_size = sizeof(size_t); // in bytes; allowing the compiler to vectorize the computation
+
+    static_assert(size_t_digits == 64 || size_t_digits == 32);
+    static_assert(block_size == 8 || block_size == 4);
+
+    uint8_t buffer[block_size];
+    size_t idx = 0; // current index in buffer
+    size_t state = seed;
+
+    hasher() = default;
+    hasher(const std::type_info & type_inf) noexcept {
+        const auto type_hash = type_inf.hash_code();
+        update(&type_hash, sizeof(type_hash));
+    }
+
+    // Properties:
+    //   - update is not associative: update(a).update(b) != update(b).update(a)
+    //   - update(a ~ b) == update(a).update(b) with ~ as concatenation operator --> useful for streaming
+    //   - update("", 0) --> state unchanged with empty input
+    hasher& update(void const * bytes, size_t len) noexcept {
+        const uint8_t * c = static_cast<uint8_t const *>(bytes);
+        if (len == 0) {
+            return *this;
+        }
+        size_t processed = 0;
+
+        // first, fill the existing buffer if it's partial
+        if (idx > 0) {
+            size_t to_fill = block_size - idx;
+            if (to_fill > len) {
+                to_fill = len;
+            }
+            std::memcpy(buffer + idx, c, to_fill);
+            idx += to_fill;
+            processed += to_fill;
+            if (idx == block_size) {
+                update_block(buffer);
+                idx = 0;
+            }
+        }
+
+        // process full blocks from the remaining input
+        for (; processed + block_size <= len; processed += block_size) {
+            update_block(c + processed);
+        }
+
+        // buffer any remaining bytes
+        size_t remaining = len - processed;
+        if (remaining > 0) {
+            std::memcpy(buffer, c + processed, remaining);
+            idx = remaining;
+        }
+        return *this;
+    }
+
+    // convenience function for testing only
+    hasher& update(const std::string & s) noexcept {
+        return update(s.data(), s.size());
+    }
+
+    // finalize and get the hash value
+    // note: after calling digest, the hasher state is modified, do not call update() again
+    size_t digest() noexcept {
+        // if there are remaining bytes in buffer, fill the rest with zeros and process
+        if (idx > 0) {
+            for (size_t i = idx; i < block_size; ++i) {
+                buffer[i] = 0;
+            }
+            update_block(buffer);
+            idx = 0;
+        }
+
+        return state;
+    }
+
+private:
+    // IMPORTANT: block must have at least block_size bytes
+    void update_block(const uint8_t * block) noexcept {
+        size_t blk = static_cast<uint32_t>(block[0])
+                    | (static_cast<uint32_t>(block[1]) << 8)
+                    | (static_cast<uint32_t>(block[2]) << 16)
+                    | (static_cast<uint32_t>(block[3]) << 24);
+        if constexpr (block_size == 8) {
+            blk = blk | (static_cast<uint64_t>(block[4]) << 32)
+                      | (static_cast<uint64_t>(block[5]) << 40)
+                      | (static_cast<uint64_t>(block[6]) << 48)
+                      | (static_cast<uint64_t>(block[7]) << 56);
+        }
+        state ^= blk;
+        state *= prime;
+    }
+};
+
+} // namespace jinja