mirror of
https://github.com/LadybirdBrowser/ladybird.git
synced 2024-11-29 19:10:26 +00:00
Utilities: cut: Work exclusively with ranges
This commit is contained in:
parent
ed3a5f6b9d
commit
4d18b21fb5
Notes:
sideshowbarker
2024-07-18 01:16:40 +09:00
Author: https://github.com/timschumi Commit: https://github.com/SerenityOS/serenity/commit/4d18b21fb5e Pull-request: https://github.com/SerenityOS/serenity/pull/10849
1 changed files with 56 additions and 58 deletions
|
@ -13,44 +13,26 @@
|
|||
#include <stdlib.h>
|
||||
#include <string.h>
|
||||
|
||||
struct Index {
|
||||
enum class Type {
|
||||
SingleIndex,
|
||||
SliceIndex,
|
||||
RangedIndex
|
||||
};
|
||||
ssize_t m_from { -1 };
|
||||
ssize_t m_to { -1 };
|
||||
Type m_type { Type::SingleIndex };
|
||||
struct Range {
|
||||
size_t m_from { 1 };
|
||||
size_t m_to { SIZE_MAX };
|
||||
|
||||
bool intersects(const Index& other)
|
||||
[[nodiscard]] bool intersects(const Range& other) const
|
||||
{
|
||||
if (m_type != Type::RangedIndex)
|
||||
return m_from == other.m_from;
|
||||
|
||||
return !(other.m_from > m_to || other.m_to < m_from);
|
||||
}
|
||||
|
||||
void merge(const Range& other)
|
||||
{
|
||||
// Can't merge two ranges that are disjoint.
|
||||
VERIFY(intersects(other));
|
||||
|
||||
m_from = min(m_from, other.m_from);
|
||||
m_to = max(m_to, other.m_to);
|
||||
}
|
||||
};
|
||||
|
||||
static void add_if_not_exists(Vector<Index>& indices, Index data)
|
||||
{
|
||||
bool append_to_vector = true;
|
||||
for (auto& index : indices) {
|
||||
if (index.intersects(data)) {
|
||||
if (index.m_type == Index::Type::RangedIndex) {
|
||||
index.m_from = min(index.m_from, data.m_from);
|
||||
index.m_to = max(index.m_to, data.m_to);
|
||||
}
|
||||
append_to_vector = false;
|
||||
}
|
||||
}
|
||||
|
||||
if (append_to_vector) {
|
||||
indices.append(data);
|
||||
}
|
||||
}
|
||||
|
||||
static bool expand_list(String& list, Vector<Index>& indices)
|
||||
static bool expand_list(String& list, Vector<Range>& ranges)
|
||||
{
|
||||
Vector<String> tokens = list.split(',');
|
||||
|
||||
|
@ -66,7 +48,7 @@ static bool expand_list(String& list, Vector<Index>& indices)
|
|||
}
|
||||
|
||||
if (token[0] == '-') {
|
||||
auto index = token.substring(1, token.length() - 1).to_int();
|
||||
auto index = token.substring(1, token.length() - 1).to_uint();
|
||||
if (!index.has_value()) {
|
||||
warnln("cut: invalid byte/character position '{}'", token);
|
||||
return false;
|
||||
|
@ -77,10 +59,9 @@ static bool expand_list(String& list, Vector<Index>& indices)
|
|||
return false;
|
||||
}
|
||||
|
||||
Index tmp = { 1, index.value(), Index::Type::RangedIndex };
|
||||
add_if_not_exists(indices, tmp);
|
||||
ranges.append({ 1, index.value() });
|
||||
} else if (token[token.length() - 1] == '-') {
|
||||
auto index = token.substring(0, token.length() - 1).to_int();
|
||||
auto index = token.substring(0, token.length() - 1).to_uint();
|
||||
if (!index.has_value()) {
|
||||
warnln("cut: invalid byte/character position '{}'", token);
|
||||
return false;
|
||||
|
@ -90,18 +71,18 @@ static bool expand_list(String& list, Vector<Index>& indices)
|
|||
warnln("cut: byte/character positions are numbered from 1");
|
||||
return false;
|
||||
}
|
||||
Index tmp = { index.value(), -1, Index::Type::SliceIndex };
|
||||
add_if_not_exists(indices, tmp);
|
||||
|
||||
ranges.append({ index.value(), SIZE_MAX });
|
||||
} else {
|
||||
auto range = token.split('-');
|
||||
if (range.size() == 2) {
|
||||
auto index1 = range[0].to_int();
|
||||
auto index1 = range[0].to_uint();
|
||||
if (!index1.has_value()) {
|
||||
warnln("cut: invalid byte/character position '{}'", range[0]);
|
||||
return false;
|
||||
}
|
||||
|
||||
auto index2 = range[1].to_int();
|
||||
auto index2 = range[1].to_uint();
|
||||
if (!index2.has_value()) {
|
||||
warnln("cut: invalid byte/character position '{}'", range[1]);
|
||||
return false;
|
||||
|
@ -115,10 +96,9 @@ static bool expand_list(String& list, Vector<Index>& indices)
|
|||
return false;
|
||||
}
|
||||
|
||||
Index tmp = { index1.value(), index2.value(), Index::Type::RangedIndex };
|
||||
add_if_not_exists(indices, tmp);
|
||||
ranges.append({ index1.value(), index2.value() });
|
||||
} else if (range.size() == 1) {
|
||||
auto index = range[0].to_int();
|
||||
auto index = range[0].to_uint();
|
||||
if (!index.has_value()) {
|
||||
warnln("cut: invalid byte/character position '{}'", range[0]);
|
||||
return false;
|
||||
|
@ -129,8 +109,7 @@ static bool expand_list(String& list, Vector<Index>& indices)
|
|||
return false;
|
||||
}
|
||||
|
||||
Index tmp = { index.value(), index.value(), Index::Type::SingleIndex };
|
||||
add_if_not_exists(indices, tmp);
|
||||
ranges.append({ index.value(), index.value() });
|
||||
} else {
|
||||
warnln("cut: invalid byte or character range");
|
||||
return false;
|
||||
|
@ -141,7 +120,7 @@ static bool expand_list(String& list, Vector<Index>& indices)
|
|||
return true;
|
||||
}
|
||||
|
||||
static void cut_file(const String& file, const Vector<Index>& byte_vector)
|
||||
static void cut_file(const String& file, const Vector<Range>& byte_vector)
|
||||
{
|
||||
FILE* fp = stdin;
|
||||
if (!file.is_null()) {
|
||||
|
@ -156,19 +135,21 @@ static void cut_file(const String& file, const Vector<Index>& byte_vector)
|
|||
ssize_t line_length = 0;
|
||||
size_t line_capacity = 0;
|
||||
while ((line_length = getline(&line, &line_capacity, fp)) != -1) {
|
||||
if (line_length < 0) {
|
||||
warnln("cut: Failed to read line from file '{}'", file);
|
||||
return;
|
||||
}
|
||||
line[line_length - 1] = '\0';
|
||||
line_length--;
|
||||
|
||||
for (auto& i : byte_vector) {
|
||||
if (i.m_type == Index::Type::SliceIndex && i.m_from < line_length)
|
||||
out("{}", line + i.m_from - 1);
|
||||
else if (i.m_type == Index::Type::SingleIndex && i.m_from <= line_length)
|
||||
out("{:c}", line[i.m_from - 1]);
|
||||
else if (i.m_type == Index::Type::RangedIndex && i.m_from <= line_length) {
|
||||
auto to = i.m_to > line_length ? line_length : i.m_to;
|
||||
auto sub_string = String(line).substring(i.m_from - 1, to - i.m_from + 1);
|
||||
out("{}", sub_string);
|
||||
} else
|
||||
break;
|
||||
if (i.m_from >= (size_t) line_length)
|
||||
continue;
|
||||
|
||||
|
||||
auto to = min(i.m_to, line_length);
|
||||
auto sub_string = String(line).substring(i.m_from - 1, to - i.m_from + 1);
|
||||
out("{}", sub_string);
|
||||
}
|
||||
outln();
|
||||
}
|
||||
|
@ -197,7 +178,7 @@ int main(int argc, char** argv)
|
|||
return 1;
|
||||
}
|
||||
|
||||
Vector<Index> byte_vector;
|
||||
Vector<Range> byte_vector;
|
||||
auto expansion_successful = expand_list(byte_list, byte_vector);
|
||||
|
||||
if (!expansion_successful) {
|
||||
|
@ -207,12 +188,29 @@ int main(int argc, char** argv)
|
|||
|
||||
quick_sort(byte_vector, [](auto& a, auto& b) { return a.m_from < b.m_from; });
|
||||
|
||||
Vector<Range> disjoint_ranges;
|
||||
for (auto& range : byte_vector) {
|
||||
if (disjoint_ranges.is_empty()) {
|
||||
disjoint_ranges.append(range);
|
||||
continue;
|
||||
}
|
||||
|
||||
Range& last_range = disjoint_ranges.last();
|
||||
|
||||
if (!last_range.intersects(range)) {
|
||||
disjoint_ranges.append(range);
|
||||
continue;
|
||||
}
|
||||
|
||||
last_range.merge(range);
|
||||
}
|
||||
|
||||
if (files.is_empty())
|
||||
files.append(String());
|
||||
|
||||
/* Process each file */
|
||||
for (auto& file : files)
|
||||
cut_file(file, byte_vector);
|
||||
cut_file(file, disjoint_ranges);
|
||||
|
||||
return 0;
|
||||
}
|
||||
|
|
Loading…
Reference in a new issue