Add string.* commands for text manipulation.

Closes #1366.

src/Makefile.am

@@ -194,6 +194,7 @@ libsub_root_a_SOURCES = \
 	command_throttle.cc \
 	command_tracker.cc \
 	command_scheduler.cc \
+	command_string.cc \
 	command_ui.cc \
 	control.cc \
 	control.h \

src/command_helpers.cc

@@ -19,6 +19,7 @@ void initialize_command_groups();
 void initialize_command_throttle();
 void initialize_command_tracker();
 void initialize_command_scheduler();
+void initialize_command_string();
 void initialize_command_ui();
 
 void
@@ -37,4 +38,5 @@ initialize_commands() {
   initialize_command_throttle();
   initialize_command_tracker();
   initialize_command_scheduler();
+  initialize_command_string();
 }

src/command_string.cc

@@ -0,0 +1,359 @@
+#include "config.h"
+
+#include <algorithm>
+#include <cctype>
+#include <iterator>
+#include <set>
+#include <string>
+#include <utility>
+#include <vector>
+#include <torrent/exceptions.h>
+#include <torrent/object.h>
+
+#include "rpc/parse.h"
+#include "rpc/rpc_manager.h"
+
+#include "globals.h"
+#include "control.h"
+#include "command_helpers.h"
+
+namespace {
+
+const std::string whitespace_characters = " \t\n\r\f\v";
+
+// The byte offset of every utf-8 character in 'text', terminated by the offset
+// past the last character. Bytes that are not valid utf-8 lead bytes are
+// treated as single characters.
+std::vector<size_t>
+utf8_offsets(const std::string& text) {
+  std::vector<size_t> offsets;
+
+  for (size_t i = 0; i < text.size(); i++)
+    if (i == 0 || (static_cast<unsigned char>(text[i]) & 0xC0) != 0x80)
+      offsets.push_back(i);
+
+  offsets.push_back(text.size());
+  return offsets;
+}
+
+int64_t
+utf8_length(const std::string& text) {
+  int64_t result = 0;
+
+  for (size_t i = 0; i < text.size(); i++)
+    if (i == 0 || (static_cast<unsigned char>(text[i]) & 0xC0) != 0x80)
+      result++;
+
+  return result;
+}
+
+std::string
+utf8_substr(const std::string& text, const std::vector<size_t>& offsets, size_t first, size_t last) {
+  return text.substr(offsets[first], offsets[last] - offsets[first]);
+}
+
+std::set<std::string>
+utf8_character_set(const std::string& text) {
+  auto offsets = utf8_offsets(text);
+  std::set<std::string> result;
+
+  for (size_t i = 0; i + 1 < offsets.size(); i++)
+    result.insert(utf8_substr(text, offsets, i, i + 1));
+
+  return result;
+}
+
+std::string
+ascii_lowercase(std::string text) {
+  std::transform(text.begin(), text.end(), text.begin(), [](unsigned char c) { return std::tolower(c); });
+  return text;
+}
+
+// A 'max_count' of zero means the command accepts any number of arguments.
+void
+verify_argument_count(const char* name, const torrent::Object::list_type& args, size_t min_count, size_t max_count) {
+  if (args.size() < min_count || (max_count != 0 && args.size() > max_count))
+    throw torrent::input_error(std::string(name) + ": invalid number of arguments.");
+}
+
+const torrent::Object&
+argument_at(const torrent::Object::list_type& args, size_t index) {
+  return *std::next(args.begin(), index);
+}
+
+void
+flatten_argument(const torrent::Object& arg, std::vector<std::string>* dest) {
+  if (!arg.is_list()) {
+    dest->push_back(rpc::convert_to_string(arg));
+    return;
+  }
+
+  for (const auto& child : arg.as_list())
+    flatten_argument(child, dest);
+}
+
+// The {old, new} pairs shared by 'string.map' and 'string.replace'.
+std::pair<std::string, std::string>
+argument_to_pair(const char* name, const torrent::Object& arg) {
+  if (!arg.is_list() || arg.as_list().size() != 2)
+    throw torrent::input_error(std::string(name) + ": arguments after the text must be {old, new} pairs.");
+
+  return {rpc::convert_to_string(arg.as_list().front()), rpc::convert_to_string(arg.as_list().back())};
+}
+
+// Compares the first argument against every remaining argument, returning true
+// as soon as one of them matches.
+torrent::Object
+apply_string_predicate(const char* name, const torrent::Object::list_type& args, bool (*predicate)(const std::string&, const std::string&)) {
+  verify_argument_count(name, args, 2, 0);
+
+  auto text = rpc::convert_to_string(args.front());
+
+  for (auto itr = std::next(args.begin()); itr != args.end(); itr++)
+    if (predicate(text, rpc::convert_to_string(*itr)))
+      return int64_t(1);
+
+  return int64_t(0);
+}
+
+bool
+text_equals(const std::string& text, const std::string& other) {
+  return text == other;
+}
+
+bool
+text_starts_with(const std::string& text, const std::string& prefix) {
+  return text.size() >= prefix.size() && text.compare(0, prefix.size(), prefix) == 0;
+}
+
+bool
+text_ends_with(const std::string& text, const std::string& tail) {
+  return text.size() >= tail.size() && text.compare(text.size() - tail.size(), tail.size(), tail) == 0;
+}
+
+bool
+text_contains(const std::string& text, const std::string& needle) {
+  return text.find(needle) != std::string::npos;
+}
+
+bool
+text_contains_i(const std::string& text, const std::string& needle) {
+  return ascii_lowercase(text).find(ascii_lowercase(needle)) != std::string::npos;
+}
+
+torrent::Object
+apply_string_length(const torrent::Object::list_type& args) {
+  verify_argument_count("string.length", args, 1, 1);
+
+  return utf8_length(rpc::convert_to_string(args.front()));
+}
+
+torrent::Object
+apply_string_substr(const torrent::Object::list_type& args) {
+  verify_argument_count("string.substr", args, 1, 4);
+
+  auto text        = rpc::convert_to_string(args.front());
+  auto offsets     = utf8_offsets(text);
+  auto text_length = static_cast<int64_t>(offsets.size() - 1);
+
+  auto position = args.size() > 1 ? rpc::convert_to_value(argument_at(args, 1)) : 0;
+  auto fallback = args.size() > 3 ? rpc::convert_to_string(argument_at(args, 3)) : std::string();
+
+  // Negative positions are relative to the end of the string.
+  if (position < 0)
+    position += text_length;
+
+  if (position < 0 || position > text_length)
+    return fallback;
+
+  auto last = text_length;
+
+  if (args.size() > 2) {
+    auto count = rpc::convert_to_value(argument_at(args, 2));
+
+    if (count < 0)
+      throw torrent::input_error("string.substr: the character count cannot be negative.");
+
+    last = std::min(text_length, position + std::min(count, text_length));
+  }
+
+  return utf8_substr(text, offsets, position, last);
+}
+
+torrent::Object
+apply_string_split(const torrent::Object::list_type& args) {
+  verify_argument_count("string.split", args, 2, 2);
+
+  auto text   = rpc::convert_to_string(args.front());
+  auto delim  = rpc::convert_to_string(args.back());
+  auto result = torrent::Object::create_list();
+
+  // An empty delimiter splits the text into its utf-8 characters.
+  if (delim.empty()) {
+    auto offsets = utf8_offsets(text);
+
+    for (size_t i = 0; i + 1 < offsets.size(); i++)
+      result.as_list().push_back(utf8_substr(text, offsets, i, i + 1));
+
+    return result;
+  }
+
+  size_t first = 0;
+
+  while (true) {
+    auto pos = text.find(delim, first);
+
+    if (pos == std::string::npos) {
+      result.as_list().push_back(text.substr(first));
+      return result;
+    }
+
+    result.as_list().push_back(text.substr(first, pos - first));
+    first = pos + delim.size();
+  }
+}
+
+torrent::Object
+apply_string_join(const torrent::Object::list_type& args) {
+  verify_argument_count("string.join", args, 1, 0);
+
+  auto delim = rpc::convert_to_string(args.front());
+
+  std::vector<std::string> parts;
+
+  for (auto itr = std::next(args.begin()); itr != args.end(); itr++)
+    flatten_argument(*itr, &parts);
+
+  std::string result;
+
+  for (auto itr = parts.begin(); itr != parts.end(); itr++) {
+    if (itr != parts.begin())
+      result += delim;
+
+    result += *itr;
+  }
+
+  return result;
+}
+
+torrent::Object
+apply_string_pad(const char* name, const torrent::Object::list_type& args, bool pad_start) {
+  verify_argument_count(name, args, 2, 3);
+
+  auto text     = rpc::convert_to_string(args.front());
+  auto pad_size = rpc::convert_to_value(argument_at(args, 1));
+  auto padding  = args.size() > 2 ? rpc::convert_to_string(argument_at(args, 2)) : std::string(" ");
+
+  auto text_length = utf8_length(text);
+
+  if (pad_size <= text_length || padding.empty())
+    return text;
+
+  auto padding_offsets = utf8_offsets(padding);
+  auto padding_length  = static_cast<int64_t>(padding_offsets.size() - 1);
+
+  std::string result;
+
+  for (int64_t i = 0; i < pad_size - text_length; i++) {
+    auto index = static_cast<size_t>(i % padding_length);
+    result += utf8_substr(padding, padding_offsets, index, index + 1);
+  }
+
+  return pad_start ? result + text : text + result;
+}
+
+torrent::Object
+apply_string_strip(const char* name, const torrent::Object::list_type& args, bool strip_start, bool strip_end) {
+  verify_argument_count(name, args, 1, 0);
+
+  auto text = rpc::convert_to_string(args.front());
+
+  std::string strippable;
+
+  for (auto itr = std::next(args.begin()); itr != args.end(); itr++)
+    strippable += rpc::convert_to_string(*itr);
+
+  if (args.size() == 1)
+    strippable = whitespace_characters;
+
+  auto characters = utf8_character_set(strippable);
+  auto offsets    = utf8_offsets(text);
+
+  size_t first = 0;
+  size_t last  = offsets.size() - 1;
+
+  while (strip_start && first < last && characters.count(utf8_substr(text, offsets, first, first + 1)) != 0)
+    first++;
+
+  while (strip_end && last > first && characters.count(utf8_substr(text, offsets, last - 1, last)) != 0)
+    last--;
+
+  return utf8_substr(text, offsets, first, last);
+}
+
+torrent::Object
+apply_string_map(const torrent::Object::list_type& args) {
+  verify_argument_count("string.map", args, 2, 0);
+
+  auto text = rpc::convert_to_string(args.front());
+
+  for (auto itr = std::next(args.begin()); itr != args.end(); itr++) {
+    auto pair = argument_to_pair("string.map", *itr);
+
+    if (text == pair.first)
+      return pair.second;
+  }
+
+  return text;
+}
+
+torrent::Object
+apply_string_replace(const torrent::Object::list_type& args) {
+  verify_argument_count("string.replace", args, 2, 0);
+
+  auto text = rpc::convert_to_string(args.front());
+
+  for (auto itr = std::next(args.begin()); itr != args.end(); itr++) {
+    auto pair = argument_to_pair("string.replace", *itr);
+
+    if (pair.first.empty())
+      throw torrent::input_error("string.replace: the replaced text cannot be empty.");
+
+    for (auto pos = text.find(pair.first); pos != std::string::npos; pos = text.find(pair.first, pos + pair.second.size()))
+      text.replace(pos, pair.first.size(), pair.second);
+  }
+
+  return text;
+}
+
+}
+
+void
+initialize_command_string() {
+  // clang-format off
+  CMD2_ANY_LIST("string.length",        [](auto, const auto& args) { return apply_string_length(args); });
+  CMD2_ANY_LIST("string.substr",     [](auto, const auto& args) { return apply_string_substr(args); });
+  CMD2_ANY_LIST("string.split",      [](auto, const auto& args) { return apply_string_split(args); });
+  CMD2_ANY_LIST("string.join",       [](auto, const auto& args) { return apply_string_join(args); });
+  CMD2_ANY_LIST("string.map",        [](auto, const auto& args) { return apply_string_map(args); });
+  CMD2_ANY_LIST("string.replace",    [](auto, const auto& args) { return apply_string_replace(args); });
+
+  CMD2_ANY_LIST("string.equals",     [](auto, const auto& args) { return apply_string_predicate("string.equals", args, &text_equals); });
+  CMD2_ANY_LIST("string.starts_with", [](auto, const auto& args) { return apply_string_predicate("string.starts_with", args, &text_starts_with); });
+  CMD2_ANY_LIST("string.ends_with",   [](auto, const auto& args) { return apply_string_predicate("string.ends_with", args, &text_ends_with); });
+  CMD2_ANY_LIST("string.contains",   [](auto, const auto& args) { return apply_string_predicate("string.contains", args, &text_contains); });
+  CMD2_ANY_LIST("string.contains_i", [](auto, const auto& args) { return apply_string_predicate("string.contains_i", args, &text_contains_i); });
+
+  CMD2_ANY_LIST("string.lpad",       [](auto, const auto& args) { return apply_string_pad("string.lpad", args, true); });
+  CMD2_ANY_LIST("string.rpad",       [](auto, const auto& args) { return apply_string_pad("string.rpad", args, false); });
+
+  CMD2_ANY_LIST("string.strip",      [](auto, const auto& args) { return apply_string_strip("string.strip", args, true, true); });
+  CMD2_ANY_LIST("string.lstrip",     [](auto, const auto& args) { return apply_string_strip("string.lstrip", args, true, false); });
+  CMD2_ANY_LIST("string.rstrip",     [](auto, const auto& args) { return apply_string_strip("string.rstrip", args, false, true); });
+  // clang-format on
+
+  for (const auto name : {"string.length", "string.substr", "string.split", "string.join", "string.map", "string.replace",
+                          "string.equals", "string.starts_with", "string.ends_with", "string.contains", "string.contains_i",
+                          "string.lpad", "string.rpad", "string.strip", "string.lstrip", "string.rstrip"})
+    rpc::rpc.mark_safe(name);
+}

test/Makefile.am

@@ -51,6 +51,8 @@ rtorrent_Test_Src_SOURCES = $(rtorrent_Test_Common) \
 	src/test_command_dynamic.h \
 	src/test_command_local.cc \
 	src/test_command_local.h \
+	src/test_command_string.cc \
+	src/test_command_string.h \
 	src/test_watch_ready_queue.cc \
 	src/test_watch_ready_queue.h
 

test/src/test_command_string.cc

@@ -0,0 +1,261 @@
+#include "config.h"
+
+#include "test/src/test_command_string.h"
+
+#include "rpc/parse_commands.h"
+
+CPPUNIT_TEST_SUITE_REGISTRATION(TestCommandString);
+
+void initialize_command_string();
+
+namespace {
+
+torrent::Object
+args(std::initializer_list<torrent::Object> objects) {
+  auto result = torrent::Object::create_list();
+
+  for (const auto& object : objects)
+    result.as_list().push_back(object);
+
+  return result;
+}
+
+std::string
+call_string(const char* key, std::initializer_list<torrent::Object> objects) {
+  return rpc::commands.call_command(key, args(objects)).as_string();
+}
+
+int64_t
+call_value(const char* key, std::initializer_list<torrent::Object> objects) {
+  return rpc::commands.call_command(key, args(objects)).as_value();
+}
+
+torrent::Object::list_type
+call_list(const char* key, std::initializer_list<torrent::Object> objects) {
+  return rpc::commands.call_command(key, args(objects)).as_list();
+}
+
+// Runs a command the way a line in the configuration file would.
+torrent::Object
+parse(const char* command) {
+  return rpc::parse_command_single(rpc::make_target(), command);
+}
+
+}
+
+void
+TestCommandString::setUp() {
+  if (!rpc::commands.has("string.length"))
+    initialize_command_string();
+}
+
+void
+TestCommandString::tearDown() {
+}
+
+void
+TestCommandString::test_length() {
+  CPPUNIT_ASSERT_EQUAL(int64_t(0), call_value("string.length", {""}));
+  CPPUNIT_ASSERT_EQUAL(int64_t(3), call_value("string.length", {"abc"}));
+
+  // The length is counted in utf-8 characters, not bytes.
+  CPPUNIT_ASSERT_EQUAL(int64_t(5), call_value("string.length", {"héllo"}));
+  CPPUNIT_ASSERT_EQUAL(int64_t(3), call_value("string.length", {"日本語"}));
+
+  // Values are converted to their string representation.
+  CPPUNIT_ASSERT_EQUAL(int64_t(4), call_value("string.length", {int64_t(1234)}));
+}
+
+void
+TestCommandString::test_equals() {
+  CPPUNIT_ASSERT_EQUAL(int64_t(1), call_value("string.equals", {"abc", "abc"}));
+  CPPUNIT_ASSERT_EQUAL(int64_t(0), call_value("string.equals", {"abc", "abd"}));
+  CPPUNIT_ASSERT_EQUAL(int64_t(0), call_value("string.equals", {"abc", "ab"}));
+
+  CPPUNIT_ASSERT_EQUAL(int64_t(1), call_value("string.equals", {"abc", "x", "abc"}));
+  CPPUNIT_ASSERT_EQUAL(int64_t(0), call_value("string.equals", {"abc", "x", "y"}));
+
+  CPPUNIT_ASSERT_EQUAL(int64_t(1), call_value("string.equals", {int64_t(42), "42"}));
+}
+
+void
+TestCommandString::test_starts_with() {
+  CPPUNIT_ASSERT_EQUAL(int64_t(1), call_value("string.starts_with", {"abcdef", "abc"}));
+  CPPUNIT_ASSERT_EQUAL(int64_t(1), call_value("string.starts_with", {"abcdef", ""}));
+  CPPUNIT_ASSERT_EQUAL(int64_t(0), call_value("string.starts_with", {"abcdef", "bcd"}));
+  CPPUNIT_ASSERT_EQUAL(int64_t(0), call_value("string.starts_with", {"ab", "abc"}));
+
+  CPPUNIT_ASSERT_EQUAL(int64_t(1), call_value("string.starts_with", {"abcdef", "x", "ab"}));
+}
+
+void
+TestCommandString::test_ends_with() {
+  CPPUNIT_ASSERT_EQUAL(int64_t(1), call_value("string.ends_with", {"abcdef", "def"}));
+  CPPUNIT_ASSERT_EQUAL(int64_t(1), call_value("string.ends_with", {"abcdef", ""}));
+  CPPUNIT_ASSERT_EQUAL(int64_t(0), call_value("string.ends_with", {"abcdef", "cde"}));
+  CPPUNIT_ASSERT_EQUAL(int64_t(0), call_value("string.ends_with", {"ef", "def"}));
+
+  CPPUNIT_ASSERT_EQUAL(int64_t(1), call_value("string.ends_with", {"a.torrent", ".rar", ".torrent"}));
+}
+
+void
+TestCommandString::test_contains() {
+  CPPUNIT_ASSERT_EQUAL(int64_t(1), call_value("string.contains", {"abcdef", "cde"}));
+  CPPUNIT_ASSERT_EQUAL(int64_t(0), call_value("string.contains", {"abcdef", "ace"}));
+  CPPUNIT_ASSERT_EQUAL(int64_t(1), call_value("string.contains", {"abcdef", "x", "bcd"}));
+
+  CPPUNIT_ASSERT_EQUAL(int64_t(0), call_value("string.contains", {"retracker.local", "RETRACKER"}));
+  CPPUNIT_ASSERT_EQUAL(int64_t(1), call_value("string.contains_i", {"retracker.local", "RETRACKER"}));
+  CPPUNIT_ASSERT_EQUAL(int64_t(1), call_value("string.contains_i", {"RETRACKER.LOCAL", "retracker"}));
+  CPPUNIT_ASSERT_EQUAL(int64_t(0), call_value("string.contains_i", {"abcdef", "xyz"}));
+}
+
+void
+TestCommandString::test_substr() {
+  CPPUNIT_ASSERT_EQUAL(std::string("abcdef"), call_string("string.substr", {"abcdef"}));
+  CPPUNIT_ASSERT_EQUAL(std::string("cdef"), call_string("string.substr", {"abcdef", int64_t(2)}));
+  CPPUNIT_ASSERT_EQUAL(std::string("cde"), call_string("string.substr", {"abcdef", int64_t(2), int64_t(3)}));
+  CPPUNIT_ASSERT_EQUAL(std::string("cdef"), call_string("string.substr", {"abcdef", int64_t(2), int64_t(100)}));
+  CPPUNIT_ASSERT_EQUAL(std::string(""), call_string("string.substr", {"abcdef", int64_t(2), int64_t(0)}));
+
+  // Negative positions are relative to the end of the string.
+  CPPUNIT_ASSERT_EQUAL(std::string("ef"), call_string("string.substr", {"abcdef", int64_t(-2)}));
+  CPPUNIT_ASSERT_EQUAL(std::string("e"), call_string("string.substr", {"abcdef", int64_t(-2), int64_t(1)}));
+
+  // Out-of-bounds positions return the default value.
+  CPPUNIT_ASSERT_EQUAL(std::string(""), call_string("string.substr", {"abcdef", int64_t(10)}));
+  CPPUNIT_ASSERT_EQUAL(std::string("n/a"), call_string("string.substr", {"abcdef", int64_t(10), int64_t(1), "n/a"}));
+  CPPUNIT_ASSERT_EQUAL(std::string("n/a"), call_string("string.substr", {"abcdef", int64_t(-10), int64_t(1), "n/a"}));
+
+  // Positions and counts are in utf-8 characters, not bytes.
+  CPPUNIT_ASSERT_EQUAL(std::string("本"), call_string("string.substr", {"日本語", int64_t(1), int64_t(1)}));
+  CPPUNIT_ASSERT_EQUAL(std::string("本語"), call_string("string.substr", {"日本語", int64_t(-2)}));
+}
+
+void
+TestCommandString::test_split() {
+  auto parts = call_list("string.split", {"a,b,c", ","});
+
+  CPPUNIT_ASSERT_EQUAL(size_t(3), parts.size());
+  CPPUNIT_ASSERT_EQUAL(std::string("a"), parts.front().as_string());
+  CPPUNIT_ASSERT_EQUAL(std::string("c"), parts.back().as_string());
+
+  // Empty fields are preserved.
+  CPPUNIT_ASSERT_EQUAL(size_t(3), call_list("string.split", {"a,,b", ","}).size());
+  CPPUNIT_ASSERT_EQUAL(size_t(1), call_list("string.split", {"abc", ","}).size());
+
+  // A multi-character delimiter is matched as a whole.
+  CPPUNIT_ASSERT_EQUAL(size_t(2), call_list("string.split", {"a::b", "::"}).size());
+
+  // An empty delimiter splits the text into its utf-8 characters.
+  auto characters = call_list("string.split", {"日本語", ""});
+
+  CPPUNIT_ASSERT_EQUAL(size_t(3), characters.size());
+  CPPUNIT_ASSERT_EQUAL(std::string("日"), characters.front().as_string());
+}
+
+void
+TestCommandString::test_join() {
+  CPPUNIT_ASSERT_EQUAL(std::string("a, b"), call_string("string.join", {", ", "a", "b"}));
+  CPPUNIT_ASSERT_EQUAL(std::string("ab"), call_string("string.join", {"", "a", "b"}));
+  CPPUNIT_ASSERT_EQUAL(std::string(""), call_string("string.join", {", "}));
+  CPPUNIT_ASSERT_EQUAL(std::string("a"), call_string("string.join", {", ", "a"}));
+  CPPUNIT_ASSERT_EQUAL(std::string("1-2"), call_string("string.join", {"-", int64_t(1), int64_t(2)}));
+
+  // Lists are flattened, so the output of string.split can be joined again.
+  CPPUNIT_ASSERT_EQUAL(std::string("a-b-c"), call_string("string.join", {"-", args({"a", "b"}), "c"}));
+}
+
+void
+TestCommandString::test_pad() {
+  CPPUNIT_ASSERT_EQUAL(std::string("  7"), call_string("string.lpad", {"7", int64_t(3)}));
+  CPPUNIT_ASSERT_EQUAL(std::string("7  "), call_string("string.rpad", {"7", int64_t(3)}));
+  CPPUNIT_ASSERT_EQUAL(std::string("007"), call_string("string.lpad", {"7", int64_t(3), "0"}));
+  CPPUNIT_ASSERT_EQUAL(std::string("700"), call_string("string.rpad", {"7", int64_t(3), "0"}));
+
+  // Text that is already long enough is returned unchanged.
+  CPPUNIT_ASSERT_EQUAL(std::string("abcd"), call_string("string.lpad", {"abcd", int64_t(2)}));
+  CPPUNIT_ASSERT_EQUAL(std::string("abcd"), call_string("string.rpad", {"abcd", int64_t(4)}));
+
+  // Multi-character padding is repeated, and an empty padding is a no-op.
+  CPPUNIT_ASSERT_EQUAL(std::string("axyx"), call_string("string.rpad", {"a", int64_t(4), "xy"}));
+  CPPUNIT_ASSERT_EQUAL(std::string("a"), call_string("string.rpad", {"a", int64_t(4), ""}));
+
+  // Padding is counted in utf-8 characters, not bytes.
+  CPPUNIT_ASSERT_EQUAL(std::string("00日"), call_string("string.lpad", {"日", int64_t(3), "0"}));
+}
+
+void
+TestCommandString::test_strip() {
+  CPPUNIT_ASSERT_EQUAL(std::string("a b"), call_string("string.strip", {"  a b  "}));
+  CPPUNIT_ASSERT_EQUAL(std::string("a"), call_string("string.strip", {"\t\n a \r\n"}));
+  CPPUNIT_ASSERT_EQUAL(std::string("a  "), call_string("string.lstrip", {"  a  "}));
+  CPPUNIT_ASSERT_EQUAL(std::string("  a"), call_string("string.rstrip", {"  a  "}));
+
+  CPPUNIT_ASSERT_EQUAL(std::string("a"), call_string("string.strip", {"xxaxx", "x"}));
+  CPPUNIT_ASSERT_EQUAL(std::string("a"), call_string("string.strip", {"/x/a/x/", "/", "x"}));
+  CPPUNIT_ASSERT_EQUAL(std::string(""), call_string("string.strip", {"aaa", "a"}));
+  CPPUNIT_ASSERT_EQUAL(std::string("  a  "), call_string("string.strip", {"  a  ", ""}));
+
+  // The strippable argument is a set of utf-8 characters.
+  CPPUNIT_ASSERT_EQUAL(std::string("a"), call_string("string.strip", {"日a日", "日"}));
+}
+
+void
+TestCommandString::test_map() {
+  CPPUNIT_ASSERT_EQUAL(std::string("b"), call_string("string.map", {"a", args({"a", "b"})}));
+  CPPUNIT_ASSERT_EQUAL(std::string("c"), call_string("string.map", {"c", args({"a", "b"})}));
+
+  // Only whole-string matches are replaced.
+  CPPUNIT_ASSERT_EQUAL(std::string("ab"), call_string("string.map", {"ab", args({"a", "b"})}));
+
+  // The first matching pair wins.
+  CPPUNIT_ASSERT_EQUAL(std::string("y"), call_string("string.map", {"x", args({"a", "b"}), args({"x", "y"}), args({"x", "z"})}));
+}
+
+void
+TestCommandString::test_replace() {
+  CPPUNIT_ASSERT_EQUAL(std::string("a+b+c"), call_string("string.replace", {"a-b-c", args({"-", "+"})}));
+  CPPUNIT_ASSERT_EQUAL(std::string("abc"), call_string("string.replace", {"a-b-c", args({"-", ""})}));
+  CPPUNIT_ASSERT_EQUAL(std::string("a-b-c"), call_string("string.replace", {"a-b-c", args({"x", "y"})}));
+
+  // Pairs are applied in order, left to right.
+  CPPUNIT_ASSERT_EQUAL(std::string("xby"), call_string("string.replace", {"abc", args({"a", "x"}), args({"c", "y"})}));
+
+  // A replacement that contains the replaced text terminates.
+  CPPUNIT_ASSERT_EQUAL(std::string("aaaa"), call_string("string.replace", {"aa", args({"a", "aa"})}));
+}
+
+void
+TestCommandString::test_invalid_arguments() {
+  CPPUNIT_ASSERT_THROW(rpc::commands.call_command("string.length", torrent::Object()), torrent::input_error);
+  CPPUNIT_ASSERT_THROW(call_string("string.length", {"a", "b"}), torrent::input_error);
+  CPPUNIT_ASSERT_THROW(call_value("string.equals", {"a"}), torrent::input_error);
+  CPPUNIT_ASSERT_THROW(call_value("string.contains", {"a"}), torrent::input_error);
+  CPPUNIT_ASSERT_THROW(call_list("string.split", {"a"}), torrent::input_error);
+  CPPUNIT_ASSERT_THROW(call_string("string.lpad", {"a"}), torrent::input_error);
+
+  // The character count of string.substr cannot be negative.
+  CPPUNIT_ASSERT_THROW(call_string("string.substr", {"abc", int64_t(0), int64_t(-1)}), torrent::input_error);
+
+  // Both string.map and string.replace require {old, new} pairs.
+  CPPUNIT_ASSERT_THROW(call_string("string.map", {"a", "b"}), torrent::input_error);
+  CPPUNIT_ASSERT_THROW(call_string("string.replace", {"a", args({"a", "b", "c"})}), torrent::input_error);
+  CPPUNIT_ASSERT_THROW(call_string("string.replace", {"a", args({"", "b"})}), torrent::input_error);
+}
+
+void
+TestCommandString::test_config_syntax() {
+  CPPUNIT_ASSERT_EQUAL(int64_t(3), parse("string.length=abc").as_value());
+  CPPUNIT_ASSERT_EQUAL(int64_t(1), parse("string.contains=retracker.local,retracker").as_value());
+  CPPUNIT_ASSERT_EQUAL(int64_t(1), parse("string.starts_with=udp://tracker.example.com,http://,udp://").as_value());
+  CPPUNIT_ASSERT_EQUAL(std::string("cde"), parse("string.substr=abcdef,2,3").as_string());
+  CPPUNIT_ASSERT_EQUAL(std::string("padded"), parse("string.strip=\"  padded  \"").as_string());
+
+  // The {old, new} pairs are written as a block in the configuration file.
+  CPPUNIT_ASSERT_EQUAL(std::string("a+b+c"), parse("string.replace=a-b-c,{-,+}").as_string());
+  CPPUNIT_ASSERT_EQUAL(std::string("y"), parse("string.map=x,{a,b},{x,y}").as_string());
+
+  // Commands nest, so a split can be joined back together.
+  CPPUNIT_ASSERT_EQUAL(std::string("a-b-c"), parse("string.join=-,(string.split,a.b.c,.)").as_string());
+}

test/src/test_command_string.h

@@ -0,0 +1,41 @@
+#include "test/helpers/test_fixture.h"
+
+class TestCommandString : public test_fixture {
+  CPPUNIT_TEST_SUITE(TestCommandString);
+
+  CPPUNIT_TEST(test_length);
+  CPPUNIT_TEST(test_equals);
+  CPPUNIT_TEST(test_starts_with);
+  CPPUNIT_TEST(test_ends_with);
+  CPPUNIT_TEST(test_contains);
+  CPPUNIT_TEST(test_substr);
+  CPPUNIT_TEST(test_split);
+  CPPUNIT_TEST(test_join);
+  CPPUNIT_TEST(test_pad);
+  CPPUNIT_TEST(test_strip);
+  CPPUNIT_TEST(test_map);
+  CPPUNIT_TEST(test_replace);
+  CPPUNIT_TEST(test_invalid_arguments);
+  CPPUNIT_TEST(test_config_syntax);
+
+  CPPUNIT_TEST_SUITE_END();
+
+public:
+  void setUp();
+  void tearDown();
+
+  void test_length();
+  void test_equals();
+  void test_starts_with();
+  void test_ends_with();
+  void test_contains();
+  void test_substr();
+  void test_split();
+  void test_join();
+  void test_pad();
+  void test_strip();
+  void test_map();
+  void test_replace();
+  void test_invalid_arguments();
+  void test_config_syntax();
+};