Struct cdx::comp::LineCompList
source · [−]pub struct LineCompList { /* private fields */ }
Expand description
Ordered list of LineComp
Implementations
sourceimpl LineCompList
impl LineCompList
sourcepub fn new() -> Self
pub fn new() -> Self
new
Examples found in repository?
More examples
6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85
pub fn main(argv: &[String], settings: &mut Settings) -> Result<()> {
let prog = args::ProgSpec::new("Sort lines.", args::FileCount::Many);
const A: [ArgSpec; 7] = [
arg! {"key", "k", "Spec", "How to compare adjacent lines"},
arg! {"unique", "u", "", "Print only first of equal lines"},
arg! {"merge", "m", "", "Merge already sorted files."},
arg! {"check", "c", "", "Check to see if each input file is sorted."},
arg! {"Check", "C", "Number", "Check to see if each input file is sorted. Report this many failures before exiting."},
arg! {"alt-sort", "a", "", "Use alternate sort algorithm"},
arg! {"alt-merge", "A", "", "Use alternate merge algorithm"},
];
let (args, files) = args::parse(&prog, &A, argv, settings)?;
let mut unique = false;
let mut merge = false;
let mut comp = LineCompList::new();
let mut check = false;
let mut num_checks = 1;
let mut config = SortConfig::default();
for x in args {
if x.name == "key" {
comp.add(&x.value)?;
} else if x.name == "alt-merge" {
config.alt_merge = true;
} else if x.name == "alt-sort" {
config.alt_sort = true;
} else if x.name == "merge" {
merge = true;
} else if x.name == "check" {
check = true;
num_checks = 1;
} else if x.name == "Check" {
check = true;
num_checks = x
.value
.to_usize_whole(x.value.as_bytes(), "number of reports")?;
} else if x.name == "unique" {
unique = true;
} else {
unreachable!();
}
}
if check && merge {
return err!("Check and Merge make no sense together");
}
if comp.is_empty() {
comp.add("")?;
}
if check {
let mut reported = 0;
for x in &files {
let mut f = Reader::new_open(x, &settings.text_in)?;
if f.is_done() {
continue;
}
loop {
if f.getline()? {
break;
}
if comp_check(&f, &mut comp, unique) {
reported += 1;
if reported >= num_checks {
break;
}
}
}
}
if reported > 0 {
return cdx_err(CdxError::Silent);
}
} else {
let mut w = get_writer("-")?;
if merge {
config.merge(&files, &mut comp, &mut w.0, unique)?;
} else {
config.sort(&files, comp, &mut w.0, unique)?;
}
}
Ok(())
}
89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184
pub fn main(argv: &[String], settings: &mut Settings) -> Result<()> {
let prog = args::ProgSpec::new("Search sorted files.", args::FileCount::Many);
const A: [ArgSpec; 5] = [
arg! {"key", "k", "Spec", "How to compare value to lines"},
arg! {"filename", "H", "ColName:Parts", "Prefix output lines with file name."},
arg! {"context", "C", "before,after", "print lines of context around matches"},
arg! {"sub-delim", "s", "Char", "Delimiter between keys for multi-column searches"},
arg_pos! {"pattern", "search string", "Search for this string in each file"},
];
let (args, files) = args::parse(&prog, &A, argv, settings)?;
let mut filename: Option<FileNameColumn> = None;
let mut context = Context::new();
let mut subdelim = b',';
let mut comp = LineCompList::new();
let mut pattern: Option<String> = None;
for x in args {
if x.name == "key" {
comp.add(&x.value)?;
} else if x.name == "filename" {
if filename.is_some() {
return err!("You cant use --filename twice");
}
let mut f = FileNameColumn::new();
f.set(&x.value)?;
filename = Some(f);
} else if x.name == "context" {
context.set(&x.value)?;
} else if x.name == "subdelim" {
if x.value.len() != 1 {
return err!("--sub-delim value must be a single character");
}
subdelim = x.value.as_bytes()[0];
} else if x.name == "pattern" {
pattern = Some(x.value);
} else {
unreachable!();
}
}
if pattern.is_none() {
return err!("The pattern is required");
}
let pattern = pattern.unwrap();
if files.is_empty() {
return err!("At least one file is required : you can't binary search stdin.");
}
if comp.is_empty() {
comp.add("1")?;
}
comp.set(pattern.as_bytes(), subdelim)?;
let mut w = get_writer("-")?;
let mut not_header: Vec<u8> = Vec::new();
for f in &files {
let m = MemMap::new(f)?;
not_header.clear();
if m.has_header() {
if filename.is_none() {
not_header.extend(m.header());
} else {
not_header.extend(b" CDX\t");
not_header.extend(filename.as_ref().unwrap().name.as_bytes());
not_header.extend(&m.header()[4..]);
}
}
if settings.checker.check(¬_header, f)? {
w.write_all(¬_header)?;
}
comp.lookup(&m.names())?;
let (mut start, mut stop) = equal_range_n(m.get(), &mut comp);
let (before, after) = context.get(start == stop);
for _x in 0..before {
if start == 0 {
break;
}
start = find_prev(m.get(), start);
}
for _x in 0..after {
stop = find_end(m.get(), stop);
}
if filename.is_none() {
write_all_nl(&mut w.0, &m.get()[start..stop])?;
} else {
let file: &FileNameColumn = filename.as_ref().unwrap();
while start < stop {
let end = find_end(m.get(), start);
w.write_all(f.tail_path_u8(file.tail, b'/').as_bytes())?;
w.write_all(&[b'\t'])?;
write_all_nl(&mut w.0, &m.get()[start..end])?;
start = end;
}
}
}
Ok(())
}
20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139
pub fn main(argv: &[String], settings: &mut Settings) -> Result<()> {
let prog = args::ProgSpec::new("Verify file contents.", args::FileCount::Many);
const A: [ArgSpec; 10] = [
arg! {"report", "r", "Number", "How many failures to report before exit."},
arg! {"first", "f", "Op,Value", "'FirstLine Op Value' must be true. E.g LT,a for first line is less than 'a'."},
arg! {"last", "l", "Op,Value", "'LastLine Op Value' must be true."},
arg! {"key", "k", "Spec", "How to compare adjacent lines"},
arg! {"sort", "s", "", "Check that the file is sorted."},
arg! {"unique", "u", "", "Check that the file is sorted, with unique lines."},
arg! {"pattern", "p", "Col,Spec,Pattern", "Select line where this col matches this pattern."},
arg! {"show-matchers", "", "", "Print available matchers"},
arg! {"show-const", "", "", "Print available constants"},
arg! {"show-func", "", "", "Print available functions"},
];
let (args, files) = args::parse(&prog, &A, argv, settings)?;
let mut list = LineMatcherList::new_with(Combiner::And);
let mut comp = LineCompList::new();
let mut do_sort = false;
let mut do_unique = false;
let mut max_fails = 5;
let mut first: Option<CheckLine> = None;
let mut last: Option<CheckLine> = None;
for x in args {
if x.name == "pattern" {
list.push(&x.value)?;
} else if x.name == "key" {
comp.add(&x.value)?;
} else if x.name == "or" {
list.multi = Combiner::Or;
} else if x.name == "fail" {
max_fails = x.value.to_usize_whole(x.value.as_bytes(), "max fails")?;
} else if x.name == "sort" {
do_sort = true;
} else if x.name == "first" {
first = Some(CheckLine::new(&x.value)?);
} else if x.name == "last" {
last = Some(CheckLine::new(&x.value)?);
} else if x.name == "unique" {
do_sort = true;
do_unique = true;
} else if x.name == "show-const" {
expr::show_const();
return Ok(());
} else if x.name == "show-func" {
expr::show_func();
return Ok(());
} else {
unreachable!();
}
}
if comp.is_empty() {
comp.add("")?;
}
let mut fails = 0;
for x in &files {
let mut f = Reader::new(&settings.text_in);
f.open(x)?;
if f.is_empty() {
continue;
}
list.lookup(&f.names())?;
comp.lookup(&f.names())?;
if f.is_done() {
continue;
}
if first.is_some()
&& !first.as_ref().unwrap().line_ok_verbose(
f.curr_line(),
&mut comp,
f.line_number(),
)?
{
fails += 1;
}
let num_cols = f.names().len();
loop {
let mut did_fail = false;
if f.curr().len() != num_cols {
eprintln!(
"Expected {num_cols} columns, but line {} of {} had {}",
f.line_number() + 1,
x,
f.curr().len()
);
did_fail = true;
}
if !list.ok_verbose(f.curr_line(), f.line_number(), x) {
did_fail = true;
}
if f.getline()? {
if last.is_some()
&& !last.as_ref().unwrap().line_ok_verbose(
f.prev_line(1),
&mut comp,
f.line_number() - 1,
)?
{
fails += 1;
}
break;
}
if do_sort {
did_fail = did_fail || comp_check(&f, &mut comp, do_unique);
}
if did_fail {
fails += 1;
if fails >= max_fails {
break;
}
}
}
if fails > 0 {
return cdx_err(CdxError::Silent);
}
}
Ok(())
}
155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293
pub fn main(argv: &[String], settings: &mut Settings) -> Result<()> {
let prog = args::ProgSpec::new("Select uniq lines.", args::FileCount::One);
const A: [ArgSpec; 7] = [
arg! {"agg", "a", "Col,Spec", "Merge value from this column, in place."},
arg! {"agg-pre", "", "NewCol,SrcCol,Spec", "Merge value from SrcCol into new column, before other columns."},
arg! {"agg-post", "", "NewCol,SrcCol,Spec", "Merge value from SrcCol into new column, after other columns."},
arg! {"key", "k", "Spec", "How to compare adjacent lines"},
arg! {"count", "c", "ColName,Position", "Write the count of matching line."},
arg! {"which", "w", "(First,Last,Min,Max)[,LineCompare]", "Which of the matching lines should be printed."},
arg! {"agg-help", "", "", "Print help for aggregators"},
];
let (args, files) = args::parse(&prog, &A, argv, settings)?;
let mut agg = LineAggList::new();
let mut comp = LineCompList::new();
let mut count = Count::default();
for x in args {
if x.name == "key" {
comp.add(&x.value)?;
} else if x.name == "count" {
count.get_count(&x.value)?;
} else if x.name == "which" {
count.get_which(&x.value)?;
} else if x.name == "agg" {
agg.push_replace(&x.value)?;
} else if x.name == "agg-post" {
agg.push_append(&x.value)?;
} else if x.name == "agg-pre" {
agg.push_prefix(&x.value)?;
} else {
unreachable!();
}
}
assert_eq!(files.len(), 1);
let mut f = Reader::new(&settings.text_in);
f.open(&files[0])?;
if f.is_empty() {
return Ok(());
}
comp.lookup(&f.names())?;
count.lookup(&f.names())?;
let mut c_write = Writer::new(settings.text_out());
if !agg.is_empty() {
if count.pos == CountPos::Begin {
agg.push_first_prefix(&format!("{},1,count", count.name))?;
}
if count.pos == CountPos::End {
agg.push_append(&format!("{},1,count", count.name))?;
}
agg.lookup(&f.names())?;
agg.fill(&mut c_write, f.header());
c_write.lookup(&f.names())?;
}
let mut w = get_writer("-")?;
if f.has_header() {
let mut ch = ColumnHeader::new();
if agg.is_empty() {
if count.pos == CountPos::Begin {
ch.push(&count.name)?;
}
ch.push_all(f.header())?;
if count.pos == CountPos::End {
ch.push(&count.name)?;
}
} else {
c_write.add_names(&mut ch, f.header())?;
}
w.write_all(ch.get_head(&settings.text_out()).as_bytes())?;
}
if f.is_done() {
return Ok(());
}
f.do_split(comp.need_split());
let mut matches = 1;
if !agg.is_empty() {
agg.add(f.curr_line());
let mut tmp = f.curr_line().clone();
loop {
if f.getline()? {
c_write.write(&mut w.0, &tmp)?;
break;
}
if comp.equal_cols(f.prev_line(1), f.curr_line()) {
count.assign(&mut tmp, f.curr_line());
agg.add(f.curr_line());
} else {
c_write.write(&mut w.0, &tmp)?;
tmp.assign(f.curr_line());
agg.reset();
agg.add(f.curr_line());
}
}
} else if count.which == Which::Last {
loop {
if f.getline()? {
count.write(&mut w.0, matches, f.prev_line(1).line(), f.delim())?;
break;
}
if comp.equal_cols(f.prev_line(1), f.curr_line()) {
matches += 1;
} else {
count.write(&mut w.0, matches, f.prev_line(1).line(), f.delim())?;
matches = 1;
}
}
} else if count.which == Which::First && count.is_plain() {
f.write_curr(&mut w.0)?;
loop {
if f.getline()? {
break;
}
if !comp.equal_cols(f.prev_line(1), f.curr_line()) {
f.write_curr(&mut w.0)?;
}
}
} else {
let mut tmp = f.curr_line().clone();
loop {
if f.getline()? {
count.write(&mut w.0, matches, tmp.line(), f.delim())?;
break;
}
if comp.equal_cols(f.prev_line(1), f.curr_line()) {
count.assign(&mut tmp, f.curr_line());
matches += 1;
} else {
count.write(&mut w.0, matches, tmp.line(), f.delim())?;
tmp.assign(f.curr_line());
matches = 1;
}
}
}
Ok(())
}
sourcepub fn is_empty(&self) -> bool
pub fn is_empty(&self) -> bool
any LineComps in the list?
Examples found in repository?
6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85
pub fn main(argv: &[String], settings: &mut Settings) -> Result<()> {
let prog = args::ProgSpec::new("Sort lines.", args::FileCount::Many);
const A: [ArgSpec; 7] = [
arg! {"key", "k", "Spec", "How to compare adjacent lines"},
arg! {"unique", "u", "", "Print only first of equal lines"},
arg! {"merge", "m", "", "Merge already sorted files."},
arg! {"check", "c", "", "Check to see if each input file is sorted."},
arg! {"Check", "C", "Number", "Check to see if each input file is sorted. Report this many failures before exiting."},
arg! {"alt-sort", "a", "", "Use alternate sort algorithm"},
arg! {"alt-merge", "A", "", "Use alternate merge algorithm"},
];
let (args, files) = args::parse(&prog, &A, argv, settings)?;
let mut unique = false;
let mut merge = false;
let mut comp = LineCompList::new();
let mut check = false;
let mut num_checks = 1;
let mut config = SortConfig::default();
for x in args {
if x.name == "key" {
comp.add(&x.value)?;
} else if x.name == "alt-merge" {
config.alt_merge = true;
} else if x.name == "alt-sort" {
config.alt_sort = true;
} else if x.name == "merge" {
merge = true;
} else if x.name == "check" {
check = true;
num_checks = 1;
} else if x.name == "Check" {
check = true;
num_checks = x
.value
.to_usize_whole(x.value.as_bytes(), "number of reports")?;
} else if x.name == "unique" {
unique = true;
} else {
unreachable!();
}
}
if check && merge {
return err!("Check and Merge make no sense together");
}
if comp.is_empty() {
comp.add("")?;
}
if check {
let mut reported = 0;
for x in &files {
let mut f = Reader::new_open(x, &settings.text_in)?;
if f.is_done() {
continue;
}
loop {
if f.getline()? {
break;
}
if comp_check(&f, &mut comp, unique) {
reported += 1;
if reported >= num_checks {
break;
}
}
}
}
if reported > 0 {
return cdx_err(CdxError::Silent);
}
} else {
let mut w = get_writer("-")?;
if merge {
config.merge(&files, &mut comp, &mut w.0, unique)?;
} else {
config.sort(&files, comp, &mut w.0, unique)?;
}
}
Ok(())
}
More examples
89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184
pub fn main(argv: &[String], settings: &mut Settings) -> Result<()> {
let prog = args::ProgSpec::new("Search sorted files.", args::FileCount::Many);
const A: [ArgSpec; 5] = [
arg! {"key", "k", "Spec", "How to compare value to lines"},
arg! {"filename", "H", "ColName:Parts", "Prefix output lines with file name."},
arg! {"context", "C", "before,after", "print lines of context around matches"},
arg! {"sub-delim", "s", "Char", "Delimiter between keys for multi-column searches"},
arg_pos! {"pattern", "search string", "Search for this string in each file"},
];
let (args, files) = args::parse(&prog, &A, argv, settings)?;
let mut filename: Option<FileNameColumn> = None;
let mut context = Context::new();
let mut subdelim = b',';
let mut comp = LineCompList::new();
let mut pattern: Option<String> = None;
for x in args {
if x.name == "key" {
comp.add(&x.value)?;
} else if x.name == "filename" {
if filename.is_some() {
return err!("You cant use --filename twice");
}
let mut f = FileNameColumn::new();
f.set(&x.value)?;
filename = Some(f);
} else if x.name == "context" {
context.set(&x.value)?;
} else if x.name == "subdelim" {
if x.value.len() != 1 {
return err!("--sub-delim value must be a single character");
}
subdelim = x.value.as_bytes()[0];
} else if x.name == "pattern" {
pattern = Some(x.value);
} else {
unreachable!();
}
}
if pattern.is_none() {
return err!("The pattern is required");
}
let pattern = pattern.unwrap();
if files.is_empty() {
return err!("At least one file is required : you can't binary search stdin.");
}
if comp.is_empty() {
comp.add("1")?;
}
comp.set(pattern.as_bytes(), subdelim)?;
let mut w = get_writer("-")?;
let mut not_header: Vec<u8> = Vec::new();
for f in &files {
let m = MemMap::new(f)?;
not_header.clear();
if m.has_header() {
if filename.is_none() {
not_header.extend(m.header());
} else {
not_header.extend(b" CDX\t");
not_header.extend(filename.as_ref().unwrap().name.as_bytes());
not_header.extend(&m.header()[4..]);
}
}
if settings.checker.check(¬_header, f)? {
w.write_all(¬_header)?;
}
comp.lookup(&m.names())?;
let (mut start, mut stop) = equal_range_n(m.get(), &mut comp);
let (before, after) = context.get(start == stop);
for _x in 0..before {
if start == 0 {
break;
}
start = find_prev(m.get(), start);
}
for _x in 0..after {
stop = find_end(m.get(), stop);
}
if filename.is_none() {
write_all_nl(&mut w.0, &m.get()[start..stop])?;
} else {
let file: &FileNameColumn = filename.as_ref().unwrap();
while start < stop {
let end = find_end(m.get(), start);
w.write_all(f.tail_path_u8(file.tail, b'/').as_bytes())?;
w.write_all(&[b'\t'])?;
write_all_nl(&mut w.0, &m.get()[start..end])?;
start = end;
}
}
}
Ok(())
}
20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139
pub fn main(argv: &[String], settings: &mut Settings) -> Result<()> {
let prog = args::ProgSpec::new("Verify file contents.", args::FileCount::Many);
const A: [ArgSpec; 10] = [
arg! {"report", "r", "Number", "How many failures to report before exit."},
arg! {"first", "f", "Op,Value", "'FirstLine Op Value' must be true. E.g LT,a for first line is less than 'a'."},
arg! {"last", "l", "Op,Value", "'LastLine Op Value' must be true."},
arg! {"key", "k", "Spec", "How to compare adjacent lines"},
arg! {"sort", "s", "", "Check that the file is sorted."},
arg! {"unique", "u", "", "Check that the file is sorted, with unique lines."},
arg! {"pattern", "p", "Col,Spec,Pattern", "Select line where this col matches this pattern."},
arg! {"show-matchers", "", "", "Print available matchers"},
arg! {"show-const", "", "", "Print available constants"},
arg! {"show-func", "", "", "Print available functions"},
];
let (args, files) = args::parse(&prog, &A, argv, settings)?;
let mut list = LineMatcherList::new_with(Combiner::And);
let mut comp = LineCompList::new();
let mut do_sort = false;
let mut do_unique = false;
let mut max_fails = 5;
let mut first: Option<CheckLine> = None;
let mut last: Option<CheckLine> = None;
for x in args {
if x.name == "pattern" {
list.push(&x.value)?;
} else if x.name == "key" {
comp.add(&x.value)?;
} else if x.name == "or" {
list.multi = Combiner::Or;
} else if x.name == "fail" {
max_fails = x.value.to_usize_whole(x.value.as_bytes(), "max fails")?;
} else if x.name == "sort" {
do_sort = true;
} else if x.name == "first" {
first = Some(CheckLine::new(&x.value)?);
} else if x.name == "last" {
last = Some(CheckLine::new(&x.value)?);
} else if x.name == "unique" {
do_sort = true;
do_unique = true;
} else if x.name == "show-const" {
expr::show_const();
return Ok(());
} else if x.name == "show-func" {
expr::show_func();
return Ok(());
} else {
unreachable!();
}
}
if comp.is_empty() {
comp.add("")?;
}
let mut fails = 0;
for x in &files {
let mut f = Reader::new(&settings.text_in);
f.open(x)?;
if f.is_empty() {
continue;
}
list.lookup(&f.names())?;
comp.lookup(&f.names())?;
if f.is_done() {
continue;
}
if first.is_some()
&& !first.as_ref().unwrap().line_ok_verbose(
f.curr_line(),
&mut comp,
f.line_number(),
)?
{
fails += 1;
}
let num_cols = f.names().len();
loop {
let mut did_fail = false;
if f.curr().len() != num_cols {
eprintln!(
"Expected {num_cols} columns, but line {} of {} had {}",
f.line_number() + 1,
x,
f.curr().len()
);
did_fail = true;
}
if !list.ok_verbose(f.curr_line(), f.line_number(), x) {
did_fail = true;
}
if f.getline()? {
if last.is_some()
&& !last.as_ref().unwrap().line_ok_verbose(
f.prev_line(1),
&mut comp,
f.line_number() - 1,
)?
{
fails += 1;
}
break;
}
if do_sort {
did_fail = did_fail || comp_check(&f, &mut comp, do_unique);
}
if did_fail {
fails += 1;
if fails >= max_fails {
break;
}
}
}
if fails > 0 {
return cdx_err(CdxError::Silent);
}
}
Ok(())
}
sourcepub fn used_cols(&self, file_num: usize) -> Vec<usize>ⓘNotable traits for Vec<u8, A>impl<A> Write for Vec<u8, A> where
A: Allocator,
pub fn used_cols(&self, file_num: usize) -> Vec<usize>ⓘNotable traits for Vec<u8, A>impl<A> Write for Vec<u8, A> where
A: Allocator,
A: Allocator,
which columns used as part of key?
Examples found in repository?
164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250
fn join(&mut self, config: &JoinConfig) -> Result<()> {
if config.infiles.len() < 2 {
return err!(
"Join requires at least two input files, {} found",
config.infiles.len()
);
}
for x in &config.infiles {
self.r.push(Reader::new_open2(x)?);
}
for _x in 0..config.infiles.len() {
self.no_match.push(None)
}
for x in &config.unmatch_out {
if (x.file_num < 1) || (x.file_num > config.infiles.len()) {
return err!(
"Join had {} input files, but requested non matching lines from file {}",
config.infiles.len(),
x.file_num
);
}
let num = x.file_num - 1;
if self.no_match[num].is_none() {
let mut w = get_writer(&x.file_name)?;
self.r[num].write_header(&mut *w)?;
self.no_match[num] = Some(w);
} else {
return err!("Multiple uses of --also for file {}", x.file_num);
}
}
if config.keys.is_empty() {
self.comp.push(CompMaker::make_line_comp("1")?);
} else {
for x in &config.keys {
self.comp.push(CompMaker::make_line_comp(x)?);
}
}
for i in 0..self.r.len() {
self.comp.lookup_n(&self.r[i].names(), i)?;
}
if config.col_specs.is_empty() {
for f in 0..self.r.len() {
let used = self.comp.used_cols(f);
for x in 0..self.r[f].names().len() {
if (f == 0) || !used.contains(&x) {
self.out_cols.push(OneOutCol::new_plain(f, x));
}
}
}
} else {
for x in &config.col_specs {
let mut x = x.clone();
if x.file >= self.r.len() {
return err!(
"{} input files, but file {} referred to as an output column",
self.r.len(),
x.file
);
}
x.cols.lookup(&self.r[x.file].names())?;
for y in x.cols.get_cols() {
self.out_cols.push(OneOutCol::new(x.file, y));
}
}
}
if self.out_cols.is_empty() {
return err!("No output columns specified");
}
if self.r[0].has_header() {
self.yes_match.write_all(b" CDX")?;
for x in &self.out_cols {
self.yes_match.write_all(&[config.out_delim])?;
x.write_head(&mut *self.yes_match, &self.r)?;
}
self.yes_match.0.write_all(&[b'\n'])?;
}
if config.jtype == JoinType::Quick {
self.join_quick(config)
} else {
err!("Only quick supported")
}
}
sourcepub fn add(&mut self, x: &str) -> Result<()>
pub fn add(&mut self, x: &str) -> Result<()>
add
Examples found in repository?
6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85
pub fn main(argv: &[String], settings: &mut Settings) -> Result<()> {
let prog = args::ProgSpec::new("Sort lines.", args::FileCount::Many);
const A: [ArgSpec; 7] = [
arg! {"key", "k", "Spec", "How to compare adjacent lines"},
arg! {"unique", "u", "", "Print only first of equal lines"},
arg! {"merge", "m", "", "Merge already sorted files."},
arg! {"check", "c", "", "Check to see if each input file is sorted."},
arg! {"Check", "C", "Number", "Check to see if each input file is sorted. Report this many failures before exiting."},
arg! {"alt-sort", "a", "", "Use alternate sort algorithm"},
arg! {"alt-merge", "A", "", "Use alternate merge algorithm"},
];
let (args, files) = args::parse(&prog, &A, argv, settings)?;
let mut unique = false;
let mut merge = false;
let mut comp = LineCompList::new();
let mut check = false;
let mut num_checks = 1;
let mut config = SortConfig::default();
for x in args {
if x.name == "key" {
comp.add(&x.value)?;
} else if x.name == "alt-merge" {
config.alt_merge = true;
} else if x.name == "alt-sort" {
config.alt_sort = true;
} else if x.name == "merge" {
merge = true;
} else if x.name == "check" {
check = true;
num_checks = 1;
} else if x.name == "Check" {
check = true;
num_checks = x
.value
.to_usize_whole(x.value.as_bytes(), "number of reports")?;
} else if x.name == "unique" {
unique = true;
} else {
unreachable!();
}
}
if check && merge {
return err!("Check and Merge make no sense together");
}
if comp.is_empty() {
comp.add("")?;
}
if check {
let mut reported = 0;
for x in &files {
let mut f = Reader::new_open(x, &settings.text_in)?;
if f.is_done() {
continue;
}
loop {
if f.getline()? {
break;
}
if comp_check(&f, &mut comp, unique) {
reported += 1;
if reported >= num_checks {
break;
}
}
}
}
if reported > 0 {
return cdx_err(CdxError::Silent);
}
} else {
let mut w = get_writer("-")?;
if merge {
config.merge(&files, &mut comp, &mut w.0, unique)?;
} else {
config.sort(&files, comp, &mut w.0, unique)?;
}
}
Ok(())
}
More examples
89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184
pub fn main(argv: &[String], settings: &mut Settings) -> Result<()> {
let prog = args::ProgSpec::new("Search sorted files.", args::FileCount::Many);
const A: [ArgSpec; 5] = [
arg! {"key", "k", "Spec", "How to compare value to lines"},
arg! {"filename", "H", "ColName:Parts", "Prefix output lines with file name."},
arg! {"context", "C", "before,after", "print lines of context around matches"},
arg! {"sub-delim", "s", "Char", "Delimiter between keys for multi-column searches"},
arg_pos! {"pattern", "search string", "Search for this string in each file"},
];
let (args, files) = args::parse(&prog, &A, argv, settings)?;
let mut filename: Option<FileNameColumn> = None;
let mut context = Context::new();
let mut subdelim = b',';
let mut comp = LineCompList::new();
let mut pattern: Option<String> = None;
for x in args {
if x.name == "key" {
comp.add(&x.value)?;
} else if x.name == "filename" {
if filename.is_some() {
return err!("You cant use --filename twice");
}
let mut f = FileNameColumn::new();
f.set(&x.value)?;
filename = Some(f);
} else if x.name == "context" {
context.set(&x.value)?;
} else if x.name == "subdelim" {
if x.value.len() != 1 {
return err!("--sub-delim value must be a single character");
}
subdelim = x.value.as_bytes()[0];
} else if x.name == "pattern" {
pattern = Some(x.value);
} else {
unreachable!();
}
}
if pattern.is_none() {
return err!("The pattern is required");
}
let pattern = pattern.unwrap();
if files.is_empty() {
return err!("At least one file is required : you can't binary search stdin.");
}
if comp.is_empty() {
comp.add("1")?;
}
comp.set(pattern.as_bytes(), subdelim)?;
let mut w = get_writer("-")?;
let mut not_header: Vec<u8> = Vec::new();
for f in &files {
let m = MemMap::new(f)?;
not_header.clear();
if m.has_header() {
if filename.is_none() {
not_header.extend(m.header());
} else {
not_header.extend(b" CDX\t");
not_header.extend(filename.as_ref().unwrap().name.as_bytes());
not_header.extend(&m.header()[4..]);
}
}
if settings.checker.check(¬_header, f)? {
w.write_all(¬_header)?;
}
comp.lookup(&m.names())?;
let (mut start, mut stop) = equal_range_n(m.get(), &mut comp);
let (before, after) = context.get(start == stop);
for _x in 0..before {
if start == 0 {
break;
}
start = find_prev(m.get(), start);
}
for _x in 0..after {
stop = find_end(m.get(), stop);
}
if filename.is_none() {
write_all_nl(&mut w.0, &m.get()[start..stop])?;
} else {
let file: &FileNameColumn = filename.as_ref().unwrap();
while start < stop {
let end = find_end(m.get(), start);
w.write_all(f.tail_path_u8(file.tail, b'/').as_bytes())?;
w.write_all(&[b'\t'])?;
write_all_nl(&mut w.0, &m.get()[start..end])?;
start = end;
}
}
}
Ok(())
}
20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139
pub fn main(argv: &[String], settings: &mut Settings) -> Result<()> {
let prog = args::ProgSpec::new("Verify file contents.", args::FileCount::Many);
const A: [ArgSpec; 10] = [
arg! {"report", "r", "Number", "How many failures to report before exit."},
arg! {"first", "f", "Op,Value", "'FirstLine Op Value' must be true. E.g LT,a for first line is less than 'a'."},
arg! {"last", "l", "Op,Value", "'LastLine Op Value' must be true."},
arg! {"key", "k", "Spec", "How to compare adjacent lines"},
arg! {"sort", "s", "", "Check that the file is sorted."},
arg! {"unique", "u", "", "Check that the file is sorted, with unique lines."},
arg! {"pattern", "p", "Col,Spec,Pattern", "Select line where this col matches this pattern."},
arg! {"show-matchers", "", "", "Print available matchers"},
arg! {"show-const", "", "", "Print available constants"},
arg! {"show-func", "", "", "Print available functions"},
];
let (args, files) = args::parse(&prog, &A, argv, settings)?;
let mut list = LineMatcherList::new_with(Combiner::And);
let mut comp = LineCompList::new();
let mut do_sort = false;
let mut do_unique = false;
let mut max_fails = 5;
let mut first: Option<CheckLine> = None;
let mut last: Option<CheckLine> = None;
for x in args {
if x.name == "pattern" {
list.push(&x.value)?;
} else if x.name == "key" {
comp.add(&x.value)?;
} else if x.name == "or" {
list.multi = Combiner::Or;
} else if x.name == "fail" {
max_fails = x.value.to_usize_whole(x.value.as_bytes(), "max fails")?;
} else if x.name == "sort" {
do_sort = true;
} else if x.name == "first" {
first = Some(CheckLine::new(&x.value)?);
} else if x.name == "last" {
last = Some(CheckLine::new(&x.value)?);
} else if x.name == "unique" {
do_sort = true;
do_unique = true;
} else if x.name == "show-const" {
expr::show_const();
return Ok(());
} else if x.name == "show-func" {
expr::show_func();
return Ok(());
} else {
unreachable!();
}
}
if comp.is_empty() {
comp.add("")?;
}
let mut fails = 0;
for x in &files {
let mut f = Reader::new(&settings.text_in);
f.open(x)?;
if f.is_empty() {
continue;
}
list.lookup(&f.names())?;
comp.lookup(&f.names())?;
if f.is_done() {
continue;
}
if first.is_some()
&& !first.as_ref().unwrap().line_ok_verbose(
f.curr_line(),
&mut comp,
f.line_number(),
)?
{
fails += 1;
}
let num_cols = f.names().len();
loop {
let mut did_fail = false;
if f.curr().len() != num_cols {
eprintln!(
"Expected {num_cols} columns, but line {} of {} had {}",
f.line_number() + 1,
x,
f.curr().len()
);
did_fail = true;
}
if !list.ok_verbose(f.curr_line(), f.line_number(), x) {
did_fail = true;
}
if f.getline()? {
if last.is_some()
&& !last.as_ref().unwrap().line_ok_verbose(
f.prev_line(1),
&mut comp,
f.line_number() - 1,
)?
{
fails += 1;
}
break;
}
if do_sort {
did_fail = did_fail || comp_check(&f, &mut comp, do_unique);
}
if did_fail {
fails += 1;
if fails >= max_fails {
break;
}
}
}
if fails > 0 {
return cdx_err(CdxError::Silent);
}
}
Ok(())
}
155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293
pub fn main(argv: &[String], settings: &mut Settings) -> Result<()> {
let prog = args::ProgSpec::new("Select uniq lines.", args::FileCount::One);
const A: [ArgSpec; 7] = [
arg! {"agg", "a", "Col,Spec", "Merge value from this column, in place."},
arg! {"agg-pre", "", "NewCol,SrcCol,Spec", "Merge value from SrcCol into new column, before other columns."},
arg! {"agg-post", "", "NewCol,SrcCol,Spec", "Merge value from SrcCol into new column, after other columns."},
arg! {"key", "k", "Spec", "How to compare adjacent lines"},
arg! {"count", "c", "ColName,Position", "Write the count of matching line."},
arg! {"which", "w", "(First,Last,Min,Max)[,LineCompare]", "Which of the matching lines should be printed."},
arg! {"agg-help", "", "", "Print help for aggregators"},
];
let (args, files) = args::parse(&prog, &A, argv, settings)?;
let mut agg = LineAggList::new();
let mut comp = LineCompList::new();
let mut count = Count::default();
for x in args {
if x.name == "key" {
comp.add(&x.value)?;
} else if x.name == "count" {
count.get_count(&x.value)?;
} else if x.name == "which" {
count.get_which(&x.value)?;
} else if x.name == "agg" {
agg.push_replace(&x.value)?;
} else if x.name == "agg-post" {
agg.push_append(&x.value)?;
} else if x.name == "agg-pre" {
agg.push_prefix(&x.value)?;
} else {
unreachable!();
}
}
assert_eq!(files.len(), 1);
let mut f = Reader::new(&settings.text_in);
f.open(&files[0])?;
if f.is_empty() {
return Ok(());
}
comp.lookup(&f.names())?;
count.lookup(&f.names())?;
let mut c_write = Writer::new(settings.text_out());
if !agg.is_empty() {
if count.pos == CountPos::Begin {
agg.push_first_prefix(&format!("{},1,count", count.name))?;
}
if count.pos == CountPos::End {
agg.push_append(&format!("{},1,count", count.name))?;
}
agg.lookup(&f.names())?;
agg.fill(&mut c_write, f.header());
c_write.lookup(&f.names())?;
}
let mut w = get_writer("-")?;
if f.has_header() {
let mut ch = ColumnHeader::new();
if agg.is_empty() {
if count.pos == CountPos::Begin {
ch.push(&count.name)?;
}
ch.push_all(f.header())?;
if count.pos == CountPos::End {
ch.push(&count.name)?;
}
} else {
c_write.add_names(&mut ch, f.header())?;
}
w.write_all(ch.get_head(&settings.text_out()).as_bytes())?;
}
if f.is_done() {
return Ok(());
}
f.do_split(comp.need_split());
let mut matches = 1;
if !agg.is_empty() {
agg.add(f.curr_line());
let mut tmp = f.curr_line().clone();
loop {
if f.getline()? {
c_write.write(&mut w.0, &tmp)?;
break;
}
if comp.equal_cols(f.prev_line(1), f.curr_line()) {
count.assign(&mut tmp, f.curr_line());
agg.add(f.curr_line());
} else {
c_write.write(&mut w.0, &tmp)?;
tmp.assign(f.curr_line());
agg.reset();
agg.add(f.curr_line());
}
}
} else if count.which == Which::Last {
loop {
if f.getline()? {
count.write(&mut w.0, matches, f.prev_line(1).line(), f.delim())?;
break;
}
if comp.equal_cols(f.prev_line(1), f.curr_line()) {
matches += 1;
} else {
count.write(&mut w.0, matches, f.prev_line(1).line(), f.delim())?;
matches = 1;
}
}
} else if count.which == Which::First && count.is_plain() {
f.write_curr(&mut w.0)?;
loop {
if f.getline()? {
break;
}
if !comp.equal_cols(f.prev_line(1), f.curr_line()) {
f.write_curr(&mut w.0)?;
}
}
} else {
let mut tmp = f.curr_line().clone();
loop {
if f.getline()? {
count.write(&mut w.0, matches, tmp.line(), f.delim())?;
break;
}
if comp.equal_cols(f.prev_line(1), f.curr_line()) {
count.assign(&mut tmp, f.curr_line());
matches += 1;
} else {
count.write(&mut w.0, matches, tmp.line(), f.delim())?;
tmp.assign(f.curr_line());
matches = 1;
}
}
}
Ok(())
}
sourcepub fn push(&mut self, x: LineComp)
pub fn push(&mut self, x: LineComp)
add
Examples found in repository?
164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250
fn join(&mut self, config: &JoinConfig) -> Result<()> {
if config.infiles.len() < 2 {
return err!(
"Join requires at least two input files, {} found",
config.infiles.len()
);
}
for x in &config.infiles {
self.r.push(Reader::new_open2(x)?);
}
for _x in 0..config.infiles.len() {
self.no_match.push(None)
}
for x in &config.unmatch_out {
if (x.file_num < 1) || (x.file_num > config.infiles.len()) {
return err!(
"Join had {} input files, but requested non matching lines from file {}",
config.infiles.len(),
x.file_num
);
}
let num = x.file_num - 1;
if self.no_match[num].is_none() {
let mut w = get_writer(&x.file_name)?;
self.r[num].write_header(&mut *w)?;
self.no_match[num] = Some(w);
} else {
return err!("Multiple uses of --also for file {}", x.file_num);
}
}
if config.keys.is_empty() {
self.comp.push(CompMaker::make_line_comp("1")?);
} else {
for x in &config.keys {
self.comp.push(CompMaker::make_line_comp(x)?);
}
}
for i in 0..self.r.len() {
self.comp.lookup_n(&self.r[i].names(), i)?;
}
if config.col_specs.is_empty() {
for f in 0..self.r.len() {
let used = self.comp.used_cols(f);
for x in 0..self.r[f].names().len() {
if (f == 0) || !used.contains(&x) {
self.out_cols.push(OneOutCol::new_plain(f, x));
}
}
}
} else {
for x in &config.col_specs {
let mut x = x.clone();
if x.file >= self.r.len() {
return err!(
"{} input files, but file {} referred to as an output column",
self.r.len(),
x.file
);
}
x.cols.lookup(&self.r[x.file].names())?;
for y in x.cols.get_cols() {
self.out_cols.push(OneOutCol::new(x.file, y));
}
}
}
if self.out_cols.is_empty() {
return err!("No output columns specified");
}
if self.r[0].has_header() {
self.yes_match.write_all(b" CDX")?;
for x in &self.out_cols {
self.yes_match.write_all(&[config.out_delim])?;
x.write_head(&mut *self.yes_match, &self.r)?;
}
self.yes_match.0.write_all(&[b'\n'])?;
}
if config.jtype == JoinType::Quick {
self.join_quick(config)
} else {
err!("Only quick supported")
}
}
sourcepub fn comp_items(&mut self, base: &[u8], left: &Item, right: &Item) -> Ordering
pub fn comp_items(&mut self, base: &[u8], left: &Item, right: &Item) -> Ordering
compare Items
Examples found in repository?
468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704
fn do_sort(&mut self) {
if self.config.alt_sort {
do_sort_lines(&self.data, &mut self.ptrs, &mut self.cmp);
} else {
self.ptrs
.sort_by(|a, b| self.cmp.comp_items(&self.data, a, b));
}
if self.unique {
self.ptrs
.dedup_by(|a, b| self.cmp.equal_items(&self.data, a, b));
}
}
/// All files have been added, write final results
pub fn finalize(&mut self, mut w: impl Write) -> Result<()> {
self.calc();
self.do_sort();
if self.tmp_files.is_empty() {
for &x in &self.ptrs {
w.write_all(x.get(&self.data))?;
}
} else {
self.write_tmp()?;
self.config
.merge_t(&self.tmp_files, &mut self.cmp, w, self.unique, &self.tmp)?;
}
Ok(())
}
#[allow(dead_code)]
fn no_del(self) {
eprintln!(
"Not deleting {}",
self.tmp.into_path().into_os_string().to_string_lossy()
);
}
/// add another file to be sorted
pub fn add_file<W: Write>(&mut self, fname: &str, w: &mut W) -> Result<()> {
let mut f = get_reader(fname)?;
let mut first_line = Vec::new();
let n = f.read_until(b'\n', &mut first_line)?;
if n == 0 {
return Ok(());
}
if self.checker.check(&first_line, fname)? {
let s = make_header(&first_line);
self.cmp.lookup(&s.vec())?;
if is_cdx(&first_line) {
w.write_all(&first_line)?;
} else {
self.add_data(&first_line)?;
}
}
self.add(&mut *f)
}
}
type NodeType = Box<MergeTreeItem>;
struct NodeData {
left: NodeType,
right: NodeType,
left_data: Option<usize>,
right_data: Option<usize>,
// done : bool, Optimization?
}
impl NodeData {
fn new(left: NodeType, right: NodeType) -> Self {
Self {
left,
right,
left_data: None,
right_data: None,
}
}
fn left_cols<'a>(&self, files: &'a [Reader]) -> &'a TextLine {
files[self.left_data.unwrap()].curr_line()
}
fn right_cols<'a>(&self, files: &'a [Reader]) -> &'a TextLine {
files[self.right_data.unwrap()].curr_line()
}
}
struct LeafData {
file_num: usize,
first: bool,
}
enum MergeTreeItem {
Leaf(LeafData),
Node(NodeData),
}
impl MergeTreeItem {
fn new_tree(files: &[Reader], nums: &[usize]) -> Self {
if nums.is_empty() {
panic!("Can't make a MergeTreeItem from zero files")
} else if nums.len() == 1 {
Self::new_leaf(nums[0])
} else {
let mid = nums.len() / 2;
Self::new_node(
Box::new(Self::new_tree(files, &nums[..mid])),
Box::new(Self::new_tree(files, &nums[mid..])),
)
}
}
fn new_node(left: NodeType, right: NodeType) -> Self {
Self::Node(NodeData::new(left, right))
}
const fn new_leaf(r: usize) -> Self {
Self::Leaf(LeafData {
file_num: r,
first: true,
})
}
fn next(&mut self, cmp: &mut LineCompList, files: &mut [Reader]) -> Result<Option<usize>> {
match self {
Self::Leaf(r) => {
if files[r.file_num].is_done() {
Ok(None)
} else {
if r.first {
r.first = false;
} else if files[r.file_num].getline()? {
return Ok(None);
}
Ok(Some(r.file_num))
}
}
Self::Node(n) => {
if n.left_data.is_none() {
n.left_data = n.left.next(cmp, files)?;
}
if n.right_data.is_none() {
n.right_data = n.right.next(cmp, files)?;
}
if n.left_data.is_none() && n.right_data.is_none() {
Ok(None)
} else if n.left_data.is_none() {
let tmp = n.right_data;
n.right_data = None;
Ok(tmp)
} else if n.right_data.is_none() {
let tmp = n.left_data;
n.left_data = None;
Ok(tmp)
} else {
let c = cmp.comp_cols(n.left_cols(files), n.right_cols(files));
if c == Ordering::Greater {
let tmp = n.right_data;
n.right_data = None;
Ok(tmp)
} else {
let tmp = n.left_data;
n.left_data = None;
Ok(tmp)
}
}
}
}
}
}
#[allow(dead_code)]
fn merge_lines(
data: &[u8],
dst: &mut [Item],
mut low: &[Item],
mut hi_start: usize,
hi_end: usize,
cmp: &mut LineCompList,
) {
let mut dst_pos = 0;
loop {
if cmp.comp_items(data, &low[0], &dst[hi_start]) != Ordering::Greater {
dst[dst_pos] = low[0];
dst_pos += 1;
low = &low[1..];
if low.is_empty() {
/* HI - NHI equalled T - (NLO + NHI) when this function
began. Therefore HI must equal T now, and there is no
need to copy from HI to T. */
break;
}
} else {
dst[dst_pos] = dst[hi_start];
dst_pos += 1;
hi_start += 1;
if hi_start == hi_end {
while !low.is_empty() {
dst[dst_pos] = low[0];
dst_pos += 1;
low = &low[1..];
}
break;
}
}
}
}
#[allow(dead_code)]
fn sort_lines(data: &[u8], items: &mut [Item], temp: &mut [Item], cmp: &mut LineCompList) {
if items.len() == 2 {
if cmp.comp_items(data, &items[0], &items[1]) == Ordering::Greater {
items.swap(0, 1);
}
} else {
let low = items.len() / 2;
sort_lines(data, &mut items[low..], temp, cmp);
if low == 1 {
temp[0] = items[0]
} else {
sort_lines_temp(data, &mut items[..low], temp, cmp);
}
merge_lines(data, items, &temp[..low], low, items.len(), cmp);
}
}
// Like sort_lines but output into temp, rather than sorting in place
#[allow(dead_code)]
fn sort_lines_temp(data: &[u8], items: &mut [Item], temp: &mut [Item], cmp: &mut LineCompList) {
if items.len() == 2 {
if cmp.comp_items(data, &items[0], &items[1]) == Ordering::Greater {
temp[0] = items[1];
temp[1] = items[0];
} else {
temp[0] = items[0];
temp[1] = items[1];
}
} else {
let low = items.len() / 2;
let items_len = items.len();
sort_lines_temp(data, &mut items[low..], &mut temp[low..items_len], cmp);
if low > 1 {
sort_lines(data, &mut items[..low], temp, cmp);
}
merge_lines(data, temp, &items[..low], low, items_len, cmp);
}
}
sourcepub fn equal_items(&mut self, base: &[u8], left: &Item, right: &Item) -> bool
pub fn equal_items(&mut self, base: &[u8], left: &Item, right: &Item) -> bool
compare Items
Examples found in repository?
468 469 470 471 472 473 474 475 476 477 478 479
fn do_sort(&mut self) {
if self.config.alt_sort {
do_sort_lines(&self.data, &mut self.ptrs, &mut self.cmp);
} else {
self.ptrs
.sort_by(|a, b| self.cmp.comp_items(&self.data, a, b));
}
if self.unique {
self.ptrs
.dedup_by(|a, b| self.cmp.equal_items(&self.data, a, b));
}
}
sourcepub fn comp_cols(&mut self, left: &TextLine, right: &TextLine) -> Ordering
pub fn comp_cols(&mut self, left: &TextLine, right: &TextLine) -> Ordering
compare TextLines in the same file
Examples found in repository?
24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626
fn compare(&mut self, a: usize, b: usize) -> Ordering {
self.cmp
.comp_cols(self.open[a].curr_line(), self.open[b].curr_line())
.reverse()
}
fn equal(&mut self, a: &TextLine, b: usize) -> bool {
self.cmp.equal_cols(a, self.open[b].curr_line())
}
}
/// sort configuration
#[derive(Copy, Clone, Debug, Default)]
pub struct SortConfig {
/// use a different sort algorithm
pub alt_sort: bool,
/// use a different merge algorithm
pub alt_merge: bool,
}
impl SortConfig {
/// merge all the files into w, using tmp
pub fn merge_t(
&self,
in_files: &[String],
cmp: &mut LineCompList,
w: impl Write,
unique: bool,
tmp: &TempDir,
) -> Result<()> {
eprintln!("Merging");
if self.alt_merge {
self.merge_t1(in_files, cmp, w, unique, tmp)
} else {
self.merge_t2(in_files, cmp, w, unique, tmp)
}
}
/// merge all the files into w, using tmp
pub fn merge_t2(
&self,
in_files: &[String],
cmp: &mut LineCompList,
mut w: impl Write,
unique: bool,
_tmp: &TempDir,
) -> Result<()> {
if in_files.is_empty() {
return Ok(());
}
if in_files.len() == 1 && !unique {
let r = get_reader(&in_files[0])?;
return copy(r.0, w);
}
let mc = Rc::new(RefCell::new(MergeContext {
open: Vec::with_capacity(in_files.len()),
cmp,
}));
let mut heap = BinaryHeap::new_by(|a: &usize, b: &usize| mc.borrow_mut().compare(*a, *b));
{
let mut mcm = mc.borrow_mut();
for x in in_files {
mcm.open.push(Reader::new_open2(x)?);
}
if !mcm.cmp.need_split() {
for x in &mut mcm.open {
x.do_split(false);
}
}
// FIXME -- Check Header
if mcm.open[0].has_header() {
w.write_all(mcm.open[0].header().line.as_bytes())?;
}
}
for i in 0..in_files.len() {
if !mc.borrow().open[i].is_done() {
heap.push(i)
}
}
if unique {
if heap.is_empty() {
return Ok(());
}
let first = heap.pop().unwrap();
let mut prev = mc.borrow().open[first].curr_line().clone();
if !mc.borrow_mut().open[first].getline()? {
heap.push(first);
}
w.write_all(prev.line())?;
while !heap.is_empty() {
if let Some(x) = heap.pop() {
let eq = mc.borrow_mut().equal(&prev, x);
if !eq {
let mcm = mc.borrow();
w.write_all(mcm.open[x].curr_line().line())?;
prev.assign(mcm.open[x].curr_line());
}
if !mc.borrow_mut().open[x].getline()? {
heap.push(x);
}
}
}
} else {
while !heap.is_empty() {
if let Some(x) = heap.pop() {
w.write_all(mc.borrow_mut().open[x].curr_line().line())?;
if !mc.borrow_mut().open[x].getline()? {
heap.push(x);
}
}
}
}
Ok(())
}
/// merge all the files into w, using tmp
pub fn merge_t1(
&self,
in_files: &[String],
cmp: &mut LineCompList,
mut w: impl Write,
unique: bool,
_tmp: &TempDir,
) -> Result<()> {
if in_files.is_empty() {
return Ok(());
}
if in_files.len() == 1 && !unique {
let r = get_reader(&in_files[0])?;
return copy(r.0, w);
}
let mut open_files: Vec<Reader> = Vec::with_capacity(in_files.len());
for x in in_files {
open_files.push(Reader::new_open2(x)?);
}
if !cmp.need_split() {
for x in &mut open_files {
x.do_split(false);
}
}
// FIXME -- Check Header
if open_files[0].has_header() {
w.write_all(open_files[0].header().line.as_bytes())?;
}
let nums: Vec<usize> = (0..open_files.len()).collect();
let mut mm = MergeTreeItem::new_tree(&open_files, &nums);
if unique {
let x = mm.next(cmp, &mut open_files)?;
if x.is_none() {
return Ok(());
}
let x = x.unwrap();
w.write_all(open_files[x].curr_line().line())?;
let mut prev = open_files[x].curr_line().clone();
loop {
let x = mm.next(cmp, &mut open_files)?;
if x.is_none() {
break;
}
let x = x.unwrap();
if !cmp.equal_cols(&prev, open_files[x].curr_line()) {
w.write_all(open_files[x].curr_line().line())?;
}
prev.assign(open_files[x].curr_line());
}
} else {
loop {
let x = mm.next(cmp, &mut open_files)?;
if x.is_none() {
break;
}
let x = x.unwrap();
w.write_all(open_files[x].curr_line().line())?;
}
}
Ok(())
}
/// merge all the files into w
pub fn merge(
&self,
files: &[String],
cmp: &mut LineCompList,
w: impl Write,
unique: bool,
) -> Result<()> {
let tmp = TempDir::new()?;
if self.alt_merge {
self.merge_t1(files, cmp, w, unique, &tmp)
} else {
self.merge_t2(files, cmp, w, unique, &tmp)
}
}
/*
/// given two file names, merge them into output
pub fn merge_2(
&self,
left: &str,
right: &str,
cmp: &mut LineCompList,
mut w: impl Write,
unique: bool,
) -> Result<()> {
let mut left_file = Reader::new2();
let mut right_file = Reader::new2();
left_file.open(left)?;
right_file.open(right)?;
left_file.do_split(false);
right_file.do_split(false);
cmp.lookup(&left_file.names())?;
// FIXME -- Check Header
if left_file.has_header() {
w.write_all(left_file.header().line.as_bytes())?;
}
if unique {
let mut prev: Vec<u8> = Vec::new();
while !left_file.is_done() && !right_file.is_done() {
let ord = cmp.comp_lines(left_file.curr().line(), right_file.curr().line());
if ord == Ordering::Less {
left_file.write(&mut w)?;
mem::swap(&mut prev, left_file.curr_mut().raw());
left_file.getline()?;
} else if ord == Ordering::Greater {
right_file.write(&mut w)?;
mem::swap(&mut prev, left_file.curr_mut().raw());
right_file.getline()?;
} else {
left_file.write(&mut w)?;
mem::swap(&mut prev, left_file.curr_mut().raw());
left_file.getline()?;
right_file.getline()?;
}
while !left_file.is_done() && cmp.equal_lines(left_file.curr().line(), &prev) {
left_file.getline()?;
}
while !right_file.is_done() && cmp.equal_lines(right_file.curr().line(), &prev) {
right_file.getline()?;
}
}
} else {
while !left_file.is_done() && !right_file.is_done() {
let ord = cmp.comp_lines(left_file.curr().line(), right_file.curr().line());
// if Equal, write both lines
if ord != Ordering::Less {
right_file.write(&mut w)?;
right_file.getline()?;
}
if ord != Ordering::Greater {
left_file.write(&mut w)?;
left_file.getline()?;
}
}
}
while !left_file.is_done() {
left_file.write(&mut w)?;
left_file.getline()?;
}
while !right_file.is_done() {
right_file.write(&mut w)?;
right_file.getline()?;
}
Ok(())
}
*/
/// Sort all the files together, into w
pub fn sort<W: Write>(
&self,
files: &[String],
cmp: LineCompList,
w: &mut W,
unique: bool,
) -> Result<()> // maybe return some useful stats?
{
let mut s = Sorter::new(cmp, 500000000, unique);
for fname in files {
s.add_file(fname, w)?;
}
s.finalize(w)?;
// s.no_del();
Ok(())
}
}
/// Large block of text and pointers to lines therein
#[allow(missing_debug_implementations)]
pub struct Sorter {
config: SortConfig,
ptrs: Vec<Item>,
cmp: LineCompList,
tmp: TempDir,
tmp_files: Vec<String>,
unique: bool,
checker: HeaderChecker,
// raw data. never resized smaller, so use data_used for real size
data: Vec<u8>,
// bytes of real data in Vec
data_used: usize,
// bytes of data referenced by ptrs
// a.k.a. offset of first byte not referenced by ptrs
// assert(data_calc <= data_used)
data_calc: usize,
// number of btes beyond data_calc, known to be free of newlines
// to avoid N^2 craziness with long lines
// assert(data_calc+data_nonl <= data_used)
data_nonl: usize,
}
const MAX_DATA: usize = 0x0ffffff00;
impl Sorter {
/// new Sorter
pub fn new(cmp: LineCompList, max_alloc: usize, unique: bool) -> Self {
let mut data_size = max_alloc / 2;
if data_size > MAX_DATA {
data_size = MAX_DATA;
}
let ptr_size = max_alloc / 2 / std::mem::size_of::<Item>();
Self {
config: SortConfig::default(),
ptrs: Vec::with_capacity(ptr_size),
data: Vec::with_capacity(data_size),
cmp,
tmp: TempDir::new().unwrap(), // FIXME - new should return Result
tmp_files: Vec::new(),
unique,
checker: HeaderChecker::new(),
data_used: 0,
data_calc: 0,
data_nonl: 0,
}
}
fn check(&self) -> bool {
debug_assert!(self.data_used <= self.data.len());
debug_assert!(self.data_calc <= self.data_used);
debug_assert!((self.data_calc + self.data_nonl) <= self.data_used);
true
}
// number of bytes available to write
fn avail(&self) -> usize {
self.data.len() - self.data_used
}
// try to make N bytes available, return amount actually available
fn prepare(&mut self, n: usize) -> usize {
let mut nsize = self.data_used + n;
if nsize > self.data.capacity() {
nsize = self.data.capacity();
}
if self.data.len() < nsize {
self.data.resize(nsize, 0);
}
let avail = self.avail();
if avail < n {
avail
} else {
n
}
}
/// add some more data to be sorted.
/// must be integer number of lines.
pub fn add_data(&mut self, in_data: &[u8]) -> Result<()> {
let sz = self.prepare(in_data.len());
if sz != in_data.len() {
eprintln!("Failed to prepare {}, only got {}", in_data.len(), sz);
return err!("Badness");
}
self.data[self.data_used..self.data_used + in_data.len()].copy_from_slice(in_data);
self.data_used += in_data.len();
// FIXME - add newline
Ok(())
}
/// Add another file's worth of data to the stream
/// possibly writing temporary files
pub fn add(&mut self, mut r: impl Read) -> Result<()> {
loop {
debug_assert!(self.check());
const SIZE: usize = 16 * 1024;
let sz = self.prepare(SIZE);
debug_assert!(sz > 0);
let nbytes = r.read(&mut self.data[self.data_used..self.data_used + sz])?;
if nbytes == 0 {
if self.data_used > 0 && self.data[self.data_used - 1] != b'\n' {
self.data[self.data_used] = b'\n';
self.data_used += 1;
}
return Ok(());
}
self.data_used += nbytes;
// calc new stuff
if self.data_used >= self.data.capacity() {
self.calc();
self.do_sort();
self.write_tmp()?;
}
}
}
/// Populate 'ptrs' from 'data'
fn calc(&mut self) {
self.ptrs.clear();
let mut item = Item::new();
let mut off: usize = 0;
for iter in self.data[0..self.data_used].iter().enumerate() {
if iter.1 == &b'\n' {
item.offset = off as u32;
item.size_plus = (iter.0 - off + 1) as u32;
off = iter.0 + 1;
self.cmp.fill_cache_line(&mut item, &self.data);
self.ptrs.push(item);
}
}
self.data_calc = off;
}
/// write ptrs to tmp file
fn write_tmp(&mut self) -> Result<()> {
let mut tmp_file = self.tmp.path().to_owned();
tmp_file.push(format!("sort_{}.txt", self.tmp_files.len()));
let tmp_name = tmp_file.to_str().unwrap();
let mut new_w = get_writer(tmp_name)?;
for &x in &self.ptrs {
new_w.write_all(x.get(&self.data))?;
}
self.tmp_files.push(tmp_name.to_string());
self.ptrs.clear();
let nsize = self.data.len() - self.data_calc;
for i in 0..nsize {
self.data[i] = self.data[self.data_calc + i];
}
self.data_used = nsize;
self.data_calc = 0;
Ok(())
}
/// sort and unique self.ptrs
fn do_sort(&mut self) {
if self.config.alt_sort {
do_sort_lines(&self.data, &mut self.ptrs, &mut self.cmp);
} else {
self.ptrs
.sort_by(|a, b| self.cmp.comp_items(&self.data, a, b));
}
if self.unique {
self.ptrs
.dedup_by(|a, b| self.cmp.equal_items(&self.data, a, b));
}
}
/// All files have been added, write final results
pub fn finalize(&mut self, mut w: impl Write) -> Result<()> {
self.calc();
self.do_sort();
if self.tmp_files.is_empty() {
for &x in &self.ptrs {
w.write_all(x.get(&self.data))?;
}
} else {
self.write_tmp()?;
self.config
.merge_t(&self.tmp_files, &mut self.cmp, w, self.unique, &self.tmp)?;
}
Ok(())
}
#[allow(dead_code)]
fn no_del(self) {
eprintln!(
"Not deleting {}",
self.tmp.into_path().into_os_string().to_string_lossy()
);
}
/// add another file to be sorted
pub fn add_file<W: Write>(&mut self, fname: &str, w: &mut W) -> Result<()> {
let mut f = get_reader(fname)?;
let mut first_line = Vec::new();
let n = f.read_until(b'\n', &mut first_line)?;
if n == 0 {
return Ok(());
}
if self.checker.check(&first_line, fname)? {
let s = make_header(&first_line);
self.cmp.lookup(&s.vec())?;
if is_cdx(&first_line) {
w.write_all(&first_line)?;
} else {
self.add_data(&first_line)?;
}
}
self.add(&mut *f)
}
}
type NodeType = Box<MergeTreeItem>;
struct NodeData {
left: NodeType,
right: NodeType,
left_data: Option<usize>,
right_data: Option<usize>,
// done : bool, Optimization?
}
impl NodeData {
fn new(left: NodeType, right: NodeType) -> Self {
Self {
left,
right,
left_data: None,
right_data: None,
}
}
fn left_cols<'a>(&self, files: &'a [Reader]) -> &'a TextLine {
files[self.left_data.unwrap()].curr_line()
}
fn right_cols<'a>(&self, files: &'a [Reader]) -> &'a TextLine {
files[self.right_data.unwrap()].curr_line()
}
}
struct LeafData {
file_num: usize,
first: bool,
}
enum MergeTreeItem {
Leaf(LeafData),
Node(NodeData),
}
impl MergeTreeItem {
fn new_tree(files: &[Reader], nums: &[usize]) -> Self {
if nums.is_empty() {
panic!("Can't make a MergeTreeItem from zero files")
} else if nums.len() == 1 {
Self::new_leaf(nums[0])
} else {
let mid = nums.len() / 2;
Self::new_node(
Box::new(Self::new_tree(files, &nums[..mid])),
Box::new(Self::new_tree(files, &nums[mid..])),
)
}
}
fn new_node(left: NodeType, right: NodeType) -> Self {
Self::Node(NodeData::new(left, right))
}
const fn new_leaf(r: usize) -> Self {
Self::Leaf(LeafData {
file_num: r,
first: true,
})
}
fn next(&mut self, cmp: &mut LineCompList, files: &mut [Reader]) -> Result<Option<usize>> {
match self {
Self::Leaf(r) => {
if files[r.file_num].is_done() {
Ok(None)
} else {
if r.first {
r.first = false;
} else if files[r.file_num].getline()? {
return Ok(None);
}
Ok(Some(r.file_num))
}
}
Self::Node(n) => {
if n.left_data.is_none() {
n.left_data = n.left.next(cmp, files)?;
}
if n.right_data.is_none() {
n.right_data = n.right.next(cmp, files)?;
}
if n.left_data.is_none() && n.right_data.is_none() {
Ok(None)
} else if n.left_data.is_none() {
let tmp = n.right_data;
n.right_data = None;
Ok(tmp)
} else if n.right_data.is_none() {
let tmp = n.left_data;
n.left_data = None;
Ok(tmp)
} else {
let c = cmp.comp_cols(n.left_cols(files), n.right_cols(files));
if c == Ordering::Greater {
let tmp = n.right_data;
n.right_data = None;
Ok(tmp)
} else {
let tmp = n.left_data;
n.left_data = None;
Ok(tmp)
}
}
}
}
}
More examples
1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932
pub fn comp_check(f: &Reader, cmp: &mut LineCompList, unique: bool) -> bool {
let c = cmp.comp_cols(f.prev_line(1), f.curr_line());
let bad = match c {
Ordering::Less => false,
Ordering::Equal => unique,
Ordering::Greater => true,
};
if c == Ordering::Equal && unique {
eprintln!("Lines are equal when they should be unique.");
} else if bad {
eprintln!("Lines are out of order");
}
if bad {
eprint!("{} : ", f.line_number() - 1);
prerr_n(&[f.prev_line(1).line()]);
eprint!("{} : ", f.line_number());
prerr_n(&[f.curr_line().line()]);
}
bad
}
sourcepub fn comp_cols_n(
&mut self,
left: &TextLine,
right: &TextLine,
left_file: usize,
right_file: usize
) -> Ordering
pub fn comp_cols_n(
&mut self,
left: &TextLine,
right: &TextLine,
left_file: usize,
right_file: usize
) -> Ordering
compare TextLines in different files
Examples found in repository?
More examples
251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320
fn join_quick(&mut self, config: &JoinConfig) -> Result<()> {
if !self.r[0].is_done() && !self.r[1].is_done() {
let mut cmp = self
.comp
.comp_cols_n(self.r[0].curr(), self.r[1].curr(), 0, 1);
'outer: loop {
match cmp {
Ordering::Equal => loop {
self.out_cols[0].write(&mut *self.yes_match, &self.r)?;
for x in &self.out_cols[1..] {
self.yes_match.write_all(&[config.out_delim])?;
x.write(&mut *self.yes_match, &self.r)?;
}
self.yes_match.write_all(&[b'\n'])?;
if self.r[0].getline()? {
self.r[1].getline()?;
break 'outer;
}
cmp = self
.comp
.comp_cols_n(self.r[0].curr(), self.r[1].curr(), 0, 1);
if cmp != Ordering::Equal {
if self.r[1].getline()? {
break 'outer;
}
cmp = self
.comp
.comp_cols_n(self.r[0].curr(), self.r[1].curr(), 0, 1);
break;
}
},
Ordering::Less => {
if let Some(x) = &mut self.no_match[0] {
self.r[0].write(&mut x.0)?;
}
if self.r[0].getline()? {
break;
}
cmp = self
.comp
.comp_cols_n(self.r[0].curr(), self.r[1].curr(), 0, 1);
}
Ordering::Greater => {
if let Some(x) = &mut self.no_match[1] {
self.r[1].write(&mut x.0)?;
}
if self.r[1].getline()? {
break;
}
cmp = self
.comp
.comp_cols_n(self.r[0].curr(), self.r[1].curr(), 0, 1);
}
}
}
}
while !self.r[0].is_done() {
if let Some(x) = &mut self.no_match[0] {
self.r[0].write(&mut x.0)?;
}
self.r[0].getline()?;
}
while !self.r[1].is_done() {
if let Some(x) = &mut self.no_match[1] {
self.r[1].write(&mut x.0)?;
}
self.r[1].getline()?;
}
Ok(())
}
sourcepub fn equal_cols(&mut self, left: &TextLine, right: &TextLine) -> bool
pub fn equal_cols(&mut self, left: &TextLine, right: &TextLine) -> bool
compare TextLines in the same file
Examples found in repository?
29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201
fn equal(&mut self, a: &TextLine, b: usize) -> bool {
self.cmp.equal_cols(a, self.open[b].curr_line())
}
}
/// sort configuration
#[derive(Copy, Clone, Debug, Default)]
pub struct SortConfig {
/// use a different sort algorithm
pub alt_sort: bool,
/// use a different merge algorithm
pub alt_merge: bool,
}
impl SortConfig {
/// merge all the files into w, using tmp
pub fn merge_t(
&self,
in_files: &[String],
cmp: &mut LineCompList,
w: impl Write,
unique: bool,
tmp: &TempDir,
) -> Result<()> {
eprintln!("Merging");
if self.alt_merge {
self.merge_t1(in_files, cmp, w, unique, tmp)
} else {
self.merge_t2(in_files, cmp, w, unique, tmp)
}
}
/// merge all the files into w, using tmp
pub fn merge_t2(
&self,
in_files: &[String],
cmp: &mut LineCompList,
mut w: impl Write,
unique: bool,
_tmp: &TempDir,
) -> Result<()> {
if in_files.is_empty() {
return Ok(());
}
if in_files.len() == 1 && !unique {
let r = get_reader(&in_files[0])?;
return copy(r.0, w);
}
let mc = Rc::new(RefCell::new(MergeContext {
open: Vec::with_capacity(in_files.len()),
cmp,
}));
let mut heap = BinaryHeap::new_by(|a: &usize, b: &usize| mc.borrow_mut().compare(*a, *b));
{
let mut mcm = mc.borrow_mut();
for x in in_files {
mcm.open.push(Reader::new_open2(x)?);
}
if !mcm.cmp.need_split() {
for x in &mut mcm.open {
x.do_split(false);
}
}
// FIXME -- Check Header
if mcm.open[0].has_header() {
w.write_all(mcm.open[0].header().line.as_bytes())?;
}
}
for i in 0..in_files.len() {
if !mc.borrow().open[i].is_done() {
heap.push(i)
}
}
if unique {
if heap.is_empty() {
return Ok(());
}
let first = heap.pop().unwrap();
let mut prev = mc.borrow().open[first].curr_line().clone();
if !mc.borrow_mut().open[first].getline()? {
heap.push(first);
}
w.write_all(prev.line())?;
while !heap.is_empty() {
if let Some(x) = heap.pop() {
let eq = mc.borrow_mut().equal(&prev, x);
if !eq {
let mcm = mc.borrow();
w.write_all(mcm.open[x].curr_line().line())?;
prev.assign(mcm.open[x].curr_line());
}
if !mc.borrow_mut().open[x].getline()? {
heap.push(x);
}
}
}
} else {
while !heap.is_empty() {
if let Some(x) = heap.pop() {
w.write_all(mc.borrow_mut().open[x].curr_line().line())?;
if !mc.borrow_mut().open[x].getline()? {
heap.push(x);
}
}
}
}
Ok(())
}
/// merge all the files into w, using tmp
pub fn merge_t1(
&self,
in_files: &[String],
cmp: &mut LineCompList,
mut w: impl Write,
unique: bool,
_tmp: &TempDir,
) -> Result<()> {
if in_files.is_empty() {
return Ok(());
}
if in_files.len() == 1 && !unique {
let r = get_reader(&in_files[0])?;
return copy(r.0, w);
}
let mut open_files: Vec<Reader> = Vec::with_capacity(in_files.len());
for x in in_files {
open_files.push(Reader::new_open2(x)?);
}
if !cmp.need_split() {
for x in &mut open_files {
x.do_split(false);
}
}
// FIXME -- Check Header
if open_files[0].has_header() {
w.write_all(open_files[0].header().line.as_bytes())?;
}
let nums: Vec<usize> = (0..open_files.len()).collect();
let mut mm = MergeTreeItem::new_tree(&open_files, &nums);
if unique {
let x = mm.next(cmp, &mut open_files)?;
if x.is_none() {
return Ok(());
}
let x = x.unwrap();
w.write_all(open_files[x].curr_line().line())?;
let mut prev = open_files[x].curr_line().clone();
loop {
let x = mm.next(cmp, &mut open_files)?;
if x.is_none() {
break;
}
let x = x.unwrap();
if !cmp.equal_cols(&prev, open_files[x].curr_line()) {
w.write_all(open_files[x].curr_line().line())?;
}
prev.assign(open_files[x].curr_line());
}
} else {
loop {
let x = mm.next(cmp, &mut open_files)?;
if x.is_none() {
break;
}
let x = x.unwrap();
w.write_all(open_files[x].curr_line().line())?;
}
}
Ok(())
}
More examples
155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293
pub fn main(argv: &[String], settings: &mut Settings) -> Result<()> {
let prog = args::ProgSpec::new("Select uniq lines.", args::FileCount::One);
const A: [ArgSpec; 7] = [
arg! {"agg", "a", "Col,Spec", "Merge value from this column, in place."},
arg! {"agg-pre", "", "NewCol,SrcCol,Spec", "Merge value from SrcCol into new column, before other columns."},
arg! {"agg-post", "", "NewCol,SrcCol,Spec", "Merge value from SrcCol into new column, after other columns."},
arg! {"key", "k", "Spec", "How to compare adjacent lines"},
arg! {"count", "c", "ColName,Position", "Write the count of matching line."},
arg! {"which", "w", "(First,Last,Min,Max)[,LineCompare]", "Which of the matching lines should be printed."},
arg! {"agg-help", "", "", "Print help for aggregators"},
];
let (args, files) = args::parse(&prog, &A, argv, settings)?;
let mut agg = LineAggList::new();
let mut comp = LineCompList::new();
let mut count = Count::default();
for x in args {
if x.name == "key" {
comp.add(&x.value)?;
} else if x.name == "count" {
count.get_count(&x.value)?;
} else if x.name == "which" {
count.get_which(&x.value)?;
} else if x.name == "agg" {
agg.push_replace(&x.value)?;
} else if x.name == "agg-post" {
agg.push_append(&x.value)?;
} else if x.name == "agg-pre" {
agg.push_prefix(&x.value)?;
} else {
unreachable!();
}
}
assert_eq!(files.len(), 1);
let mut f = Reader::new(&settings.text_in);
f.open(&files[0])?;
if f.is_empty() {
return Ok(());
}
comp.lookup(&f.names())?;
count.lookup(&f.names())?;
let mut c_write = Writer::new(settings.text_out());
if !agg.is_empty() {
if count.pos == CountPos::Begin {
agg.push_first_prefix(&format!("{},1,count", count.name))?;
}
if count.pos == CountPos::End {
agg.push_append(&format!("{},1,count", count.name))?;
}
agg.lookup(&f.names())?;
agg.fill(&mut c_write, f.header());
c_write.lookup(&f.names())?;
}
let mut w = get_writer("-")?;
if f.has_header() {
let mut ch = ColumnHeader::new();
if agg.is_empty() {
if count.pos == CountPos::Begin {
ch.push(&count.name)?;
}
ch.push_all(f.header())?;
if count.pos == CountPos::End {
ch.push(&count.name)?;
}
} else {
c_write.add_names(&mut ch, f.header())?;
}
w.write_all(ch.get_head(&settings.text_out()).as_bytes())?;
}
if f.is_done() {
return Ok(());
}
f.do_split(comp.need_split());
let mut matches = 1;
if !agg.is_empty() {
agg.add(f.curr_line());
let mut tmp = f.curr_line().clone();
loop {
if f.getline()? {
c_write.write(&mut w.0, &tmp)?;
break;
}
if comp.equal_cols(f.prev_line(1), f.curr_line()) {
count.assign(&mut tmp, f.curr_line());
agg.add(f.curr_line());
} else {
c_write.write(&mut w.0, &tmp)?;
tmp.assign(f.curr_line());
agg.reset();
agg.add(f.curr_line());
}
}
} else if count.which == Which::Last {
loop {
if f.getline()? {
count.write(&mut w.0, matches, f.prev_line(1).line(), f.delim())?;
break;
}
if comp.equal_cols(f.prev_line(1), f.curr_line()) {
matches += 1;
} else {
count.write(&mut w.0, matches, f.prev_line(1).line(), f.delim())?;
matches = 1;
}
}
} else if count.which == Which::First && count.is_plain() {
f.write_curr(&mut w.0)?;
loop {
if f.getline()? {
break;
}
if !comp.equal_cols(f.prev_line(1), f.curr_line()) {
f.write_curr(&mut w.0)?;
}
}
} else {
let mut tmp = f.curr_line().clone();
loop {
if f.getline()? {
count.write(&mut w.0, matches, tmp.line(), f.delim())?;
break;
}
if comp.equal_cols(f.prev_line(1), f.curr_line()) {
count.assign(&mut tmp, f.curr_line());
matches += 1;
} else {
count.write(&mut w.0, matches, tmp.line(), f.delim())?;
tmp.assign(f.curr_line());
matches = 1;
}
}
}
Ok(())
}
sourcepub fn equal_cols_n(
&mut self,
left: &TextLine,
right: &TextLine,
left_file: usize,
right_file: usize
) -> bool
pub fn equal_cols_n(
&mut self,
left: &TextLine,
right: &TextLine,
left_file: usize,
right_file: usize
) -> bool
compare TextLines in different files
sourcepub fn comp_lines(&mut self, left: &[u8], right: &[u8]) -> Ordering
pub fn comp_lines(&mut self, left: &[u8], right: &[u8]) -> Ordering
compare liness from the same
sourcepub fn comp_lines_n(
&mut self,
left: &[u8],
right: &[u8],
left_file: usize,
right_file: usize
) -> Ordering
pub fn comp_lines_n(
&mut self,
left: &[u8],
right: &[u8],
left_file: usize,
right_file: usize
) -> Ordering
compare lines from different files
sourcepub fn equal_lines(&mut self, left: &[u8], right: &[u8]) -> bool
pub fn equal_lines(&mut self, left: &[u8], right: &[u8]) -> bool
compare lines from the same file
sourcepub fn equal_lines_n(
&mut self,
left: &[u8],
right: &[u8],
left_file: usize,
right_file: usize
) -> bool
pub fn equal_lines_n(
&mut self,
left: &[u8],
right: &[u8],
left_file: usize,
right_file: usize
) -> bool
compare lines from different files
sourcepub fn lookup(&mut self, fieldnames: &[&str]) -> Result<()>
pub fn lookup(&mut self, fieldnames: &[&str]) -> Result<()>
resolve named columns
Examples found in repository?
504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521
pub fn add_file<W: Write>(&mut self, fname: &str, w: &mut W) -> Result<()> {
let mut f = get_reader(fname)?;
let mut first_line = Vec::new();
let n = f.read_until(b'\n', &mut first_line)?;
if n == 0 {
return Ok(());
}
if self.checker.check(&first_line, fname)? {
let s = make_header(&first_line);
self.cmp.lookup(&s.vec())?;
if is_cdx(&first_line) {
w.write_all(&first_line)?;
} else {
self.add_data(&first_line)?;
}
}
self.add(&mut *f)
}
More examples
89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184
pub fn main(argv: &[String], settings: &mut Settings) -> Result<()> {
let prog = args::ProgSpec::new("Search sorted files.", args::FileCount::Many);
const A: [ArgSpec; 5] = [
arg! {"key", "k", "Spec", "How to compare value to lines"},
arg! {"filename", "H", "ColName:Parts", "Prefix output lines with file name."},
arg! {"context", "C", "before,after", "print lines of context around matches"},
arg! {"sub-delim", "s", "Char", "Delimiter between keys for multi-column searches"},
arg_pos! {"pattern", "search string", "Search for this string in each file"},
];
let (args, files) = args::parse(&prog, &A, argv, settings)?;
let mut filename: Option<FileNameColumn> = None;
let mut context = Context::new();
let mut subdelim = b',';
let mut comp = LineCompList::new();
let mut pattern: Option<String> = None;
for x in args {
if x.name == "key" {
comp.add(&x.value)?;
} else if x.name == "filename" {
if filename.is_some() {
return err!("You cant use --filename twice");
}
let mut f = FileNameColumn::new();
f.set(&x.value)?;
filename = Some(f);
} else if x.name == "context" {
context.set(&x.value)?;
} else if x.name == "subdelim" {
if x.value.len() != 1 {
return err!("--sub-delim value must be a single character");
}
subdelim = x.value.as_bytes()[0];
} else if x.name == "pattern" {
pattern = Some(x.value);
} else {
unreachable!();
}
}
if pattern.is_none() {
return err!("The pattern is required");
}
let pattern = pattern.unwrap();
if files.is_empty() {
return err!("At least one file is required : you can't binary search stdin.");
}
if comp.is_empty() {
comp.add("1")?;
}
comp.set(pattern.as_bytes(), subdelim)?;
let mut w = get_writer("-")?;
let mut not_header: Vec<u8> = Vec::new();
for f in &files {
let m = MemMap::new(f)?;
not_header.clear();
if m.has_header() {
if filename.is_none() {
not_header.extend(m.header());
} else {
not_header.extend(b" CDX\t");
not_header.extend(filename.as_ref().unwrap().name.as_bytes());
not_header.extend(&m.header()[4..]);
}
}
if settings.checker.check(¬_header, f)? {
w.write_all(¬_header)?;
}
comp.lookup(&m.names())?;
let (mut start, mut stop) = equal_range_n(m.get(), &mut comp);
let (before, after) = context.get(start == stop);
for _x in 0..before {
if start == 0 {
break;
}
start = find_prev(m.get(), start);
}
for _x in 0..after {
stop = find_end(m.get(), stop);
}
if filename.is_none() {
write_all_nl(&mut w.0, &m.get()[start..stop])?;
} else {
let file: &FileNameColumn = filename.as_ref().unwrap();
while start < stop {
let end = find_end(m.get(), start);
w.write_all(f.tail_path_u8(file.tail, b'/').as_bytes())?;
w.write_all(&[b'\t'])?;
write_all_nl(&mut w.0, &m.get()[start..end])?;
start = end;
}
}
}
Ok(())
}
20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139
pub fn main(argv: &[String], settings: &mut Settings) -> Result<()> {
let prog = args::ProgSpec::new("Verify file contents.", args::FileCount::Many);
const A: [ArgSpec; 10] = [
arg! {"report", "r", "Number", "How many failures to report before exit."},
arg! {"first", "f", "Op,Value", "'FirstLine Op Value' must be true. E.g LT,a for first line is less than 'a'."},
arg! {"last", "l", "Op,Value", "'LastLine Op Value' must be true."},
arg! {"key", "k", "Spec", "How to compare adjacent lines"},
arg! {"sort", "s", "", "Check that the file is sorted."},
arg! {"unique", "u", "", "Check that the file is sorted, with unique lines."},
arg! {"pattern", "p", "Col,Spec,Pattern", "Select line where this col matches this pattern."},
arg! {"show-matchers", "", "", "Print available matchers"},
arg! {"show-const", "", "", "Print available constants"},
arg! {"show-func", "", "", "Print available functions"},
];
let (args, files) = args::parse(&prog, &A, argv, settings)?;
let mut list = LineMatcherList::new_with(Combiner::And);
let mut comp = LineCompList::new();
let mut do_sort = false;
let mut do_unique = false;
let mut max_fails = 5;
let mut first: Option<CheckLine> = None;
let mut last: Option<CheckLine> = None;
for x in args {
if x.name == "pattern" {
list.push(&x.value)?;
} else if x.name == "key" {
comp.add(&x.value)?;
} else if x.name == "or" {
list.multi = Combiner::Or;
} else if x.name == "fail" {
max_fails = x.value.to_usize_whole(x.value.as_bytes(), "max fails")?;
} else if x.name == "sort" {
do_sort = true;
} else if x.name == "first" {
first = Some(CheckLine::new(&x.value)?);
} else if x.name == "last" {
last = Some(CheckLine::new(&x.value)?);
} else if x.name == "unique" {
do_sort = true;
do_unique = true;
} else if x.name == "show-const" {
expr::show_const();
return Ok(());
} else if x.name == "show-func" {
expr::show_func();
return Ok(());
} else {
unreachable!();
}
}
if comp.is_empty() {
comp.add("")?;
}
let mut fails = 0;
for x in &files {
let mut f = Reader::new(&settings.text_in);
f.open(x)?;
if f.is_empty() {
continue;
}
list.lookup(&f.names())?;
comp.lookup(&f.names())?;
if f.is_done() {
continue;
}
if first.is_some()
&& !first.as_ref().unwrap().line_ok_verbose(
f.curr_line(),
&mut comp,
f.line_number(),
)?
{
fails += 1;
}
let num_cols = f.names().len();
loop {
let mut did_fail = false;
if f.curr().len() != num_cols {
eprintln!(
"Expected {num_cols} columns, but line {} of {} had {}",
f.line_number() + 1,
x,
f.curr().len()
);
did_fail = true;
}
if !list.ok_verbose(f.curr_line(), f.line_number(), x) {
did_fail = true;
}
if f.getline()? {
if last.is_some()
&& !last.as_ref().unwrap().line_ok_verbose(
f.prev_line(1),
&mut comp,
f.line_number() - 1,
)?
{
fails += 1;
}
break;
}
if do_sort {
did_fail = did_fail || comp_check(&f, &mut comp, do_unique);
}
if did_fail {
fails += 1;
if fails >= max_fails {
break;
}
}
}
if fails > 0 {
return cdx_err(CdxError::Silent);
}
}
Ok(())
}
155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293
pub fn main(argv: &[String], settings: &mut Settings) -> Result<()> {
let prog = args::ProgSpec::new("Select uniq lines.", args::FileCount::One);
const A: [ArgSpec; 7] = [
arg! {"agg", "a", "Col,Spec", "Merge value from this column, in place."},
arg! {"agg-pre", "", "NewCol,SrcCol,Spec", "Merge value from SrcCol into new column, before other columns."},
arg! {"agg-post", "", "NewCol,SrcCol,Spec", "Merge value from SrcCol into new column, after other columns."},
arg! {"key", "k", "Spec", "How to compare adjacent lines"},
arg! {"count", "c", "ColName,Position", "Write the count of matching line."},
arg! {"which", "w", "(First,Last,Min,Max)[,LineCompare]", "Which of the matching lines should be printed."},
arg! {"agg-help", "", "", "Print help for aggregators"},
];
let (args, files) = args::parse(&prog, &A, argv, settings)?;
let mut agg = LineAggList::new();
let mut comp = LineCompList::new();
let mut count = Count::default();
for x in args {
if x.name == "key" {
comp.add(&x.value)?;
} else if x.name == "count" {
count.get_count(&x.value)?;
} else if x.name == "which" {
count.get_which(&x.value)?;
} else if x.name == "agg" {
agg.push_replace(&x.value)?;
} else if x.name == "agg-post" {
agg.push_append(&x.value)?;
} else if x.name == "agg-pre" {
agg.push_prefix(&x.value)?;
} else {
unreachable!();
}
}
assert_eq!(files.len(), 1);
let mut f = Reader::new(&settings.text_in);
f.open(&files[0])?;
if f.is_empty() {
return Ok(());
}
comp.lookup(&f.names())?;
count.lookup(&f.names())?;
let mut c_write = Writer::new(settings.text_out());
if !agg.is_empty() {
if count.pos == CountPos::Begin {
agg.push_first_prefix(&format!("{},1,count", count.name))?;
}
if count.pos == CountPos::End {
agg.push_append(&format!("{},1,count", count.name))?;
}
agg.lookup(&f.names())?;
agg.fill(&mut c_write, f.header());
c_write.lookup(&f.names())?;
}
let mut w = get_writer("-")?;
if f.has_header() {
let mut ch = ColumnHeader::new();
if agg.is_empty() {
if count.pos == CountPos::Begin {
ch.push(&count.name)?;
}
ch.push_all(f.header())?;
if count.pos == CountPos::End {
ch.push(&count.name)?;
}
} else {
c_write.add_names(&mut ch, f.header())?;
}
w.write_all(ch.get_head(&settings.text_out()).as_bytes())?;
}
if f.is_done() {
return Ok(());
}
f.do_split(comp.need_split());
let mut matches = 1;
if !agg.is_empty() {
agg.add(f.curr_line());
let mut tmp = f.curr_line().clone();
loop {
if f.getline()? {
c_write.write(&mut w.0, &tmp)?;
break;
}
if comp.equal_cols(f.prev_line(1), f.curr_line()) {
count.assign(&mut tmp, f.curr_line());
agg.add(f.curr_line());
} else {
c_write.write(&mut w.0, &tmp)?;
tmp.assign(f.curr_line());
agg.reset();
agg.add(f.curr_line());
}
}
} else if count.which == Which::Last {
loop {
if f.getline()? {
count.write(&mut w.0, matches, f.prev_line(1).line(), f.delim())?;
break;
}
if comp.equal_cols(f.prev_line(1), f.curr_line()) {
matches += 1;
} else {
count.write(&mut w.0, matches, f.prev_line(1).line(), f.delim())?;
matches = 1;
}
}
} else if count.which == Which::First && count.is_plain() {
f.write_curr(&mut w.0)?;
loop {
if f.getline()? {
break;
}
if !comp.equal_cols(f.prev_line(1), f.curr_line()) {
f.write_curr(&mut w.0)?;
}
}
} else {
let mut tmp = f.curr_line().clone();
loop {
if f.getline()? {
count.write(&mut w.0, matches, tmp.line(), f.delim())?;
break;
}
if comp.equal_cols(f.prev_line(1), f.curr_line()) {
count.assign(&mut tmp, f.curr_line());
matches += 1;
} else {
count.write(&mut w.0, matches, tmp.line(), f.delim())?;
tmp.assign(f.curr_line());
matches = 1;
}
}
}
Ok(())
}
sourcepub fn lookup_n(&mut self, fieldnames: &[&str], file_num: usize) -> Result<()>
pub fn lookup_n(&mut self, fieldnames: &[&str], file_num: usize) -> Result<()>
resolve named columns in the given file
Examples found in repository?
More examples
164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250
fn join(&mut self, config: &JoinConfig) -> Result<()> {
if config.infiles.len() < 2 {
return err!(
"Join requires at least two input files, {} found",
config.infiles.len()
);
}
for x in &config.infiles {
self.r.push(Reader::new_open2(x)?);
}
for _x in 0..config.infiles.len() {
self.no_match.push(None)
}
for x in &config.unmatch_out {
if (x.file_num < 1) || (x.file_num > config.infiles.len()) {
return err!(
"Join had {} input files, but requested non matching lines from file {}",
config.infiles.len(),
x.file_num
);
}
let num = x.file_num - 1;
if self.no_match[num].is_none() {
let mut w = get_writer(&x.file_name)?;
self.r[num].write_header(&mut *w)?;
self.no_match[num] = Some(w);
} else {
return err!("Multiple uses of --also for file {}", x.file_num);
}
}
if config.keys.is_empty() {
self.comp.push(CompMaker::make_line_comp("1")?);
} else {
for x in &config.keys {
self.comp.push(CompMaker::make_line_comp(x)?);
}
}
for i in 0..self.r.len() {
self.comp.lookup_n(&self.r[i].names(), i)?;
}
if config.col_specs.is_empty() {
for f in 0..self.r.len() {
let used = self.comp.used_cols(f);
for x in 0..self.r[f].names().len() {
if (f == 0) || !used.contains(&x) {
self.out_cols.push(OneOutCol::new_plain(f, x));
}
}
}
} else {
for x in &config.col_specs {
let mut x = x.clone();
if x.file >= self.r.len() {
return err!(
"{} input files, but file {} referred to as an output column",
self.r.len(),
x.file
);
}
x.cols.lookup(&self.r[x.file].names())?;
for y in x.cols.get_cols() {
self.out_cols.push(OneOutCol::new(x.file, y));
}
}
}
if self.out_cols.is_empty() {
return err!("No output columns specified");
}
if self.r[0].has_header() {
self.yes_match.write_all(b" CDX")?;
for x in &self.out_cols {
self.yes_match.write_all(&[config.out_delim])?;
x.write_head(&mut *self.yes_match, &self.r)?;
}
self.yes_match.0.write_all(&[b'\n'])?;
}
if config.jtype == JoinType::Quick {
self.join_quick(config)
} else {
err!("Only quick supported")
}
}
sourcepub fn need_split(&self) -> bool
pub fn need_split(&self) -> bool
do TextLines need their columns initialized
Examples found in repository?
62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201
pub fn merge_t2(
&self,
in_files: &[String],
cmp: &mut LineCompList,
mut w: impl Write,
unique: bool,
_tmp: &TempDir,
) -> Result<()> {
if in_files.is_empty() {
return Ok(());
}
if in_files.len() == 1 && !unique {
let r = get_reader(&in_files[0])?;
return copy(r.0, w);
}
let mc = Rc::new(RefCell::new(MergeContext {
open: Vec::with_capacity(in_files.len()),
cmp,
}));
let mut heap = BinaryHeap::new_by(|a: &usize, b: &usize| mc.borrow_mut().compare(*a, *b));
{
let mut mcm = mc.borrow_mut();
for x in in_files {
mcm.open.push(Reader::new_open2(x)?);
}
if !mcm.cmp.need_split() {
for x in &mut mcm.open {
x.do_split(false);
}
}
// FIXME -- Check Header
if mcm.open[0].has_header() {
w.write_all(mcm.open[0].header().line.as_bytes())?;
}
}
for i in 0..in_files.len() {
if !mc.borrow().open[i].is_done() {
heap.push(i)
}
}
if unique {
if heap.is_empty() {
return Ok(());
}
let first = heap.pop().unwrap();
let mut prev = mc.borrow().open[first].curr_line().clone();
if !mc.borrow_mut().open[first].getline()? {
heap.push(first);
}
w.write_all(prev.line())?;
while !heap.is_empty() {
if let Some(x) = heap.pop() {
let eq = mc.borrow_mut().equal(&prev, x);
if !eq {
let mcm = mc.borrow();
w.write_all(mcm.open[x].curr_line().line())?;
prev.assign(mcm.open[x].curr_line());
}
if !mc.borrow_mut().open[x].getline()? {
heap.push(x);
}
}
}
} else {
while !heap.is_empty() {
if let Some(x) = heap.pop() {
w.write_all(mc.borrow_mut().open[x].curr_line().line())?;
if !mc.borrow_mut().open[x].getline()? {
heap.push(x);
}
}
}
}
Ok(())
}
/// merge all the files into w, using tmp
pub fn merge_t1(
&self,
in_files: &[String],
cmp: &mut LineCompList,
mut w: impl Write,
unique: bool,
_tmp: &TempDir,
) -> Result<()> {
if in_files.is_empty() {
return Ok(());
}
if in_files.len() == 1 && !unique {
let r = get_reader(&in_files[0])?;
return copy(r.0, w);
}
let mut open_files: Vec<Reader> = Vec::with_capacity(in_files.len());
for x in in_files {
open_files.push(Reader::new_open2(x)?);
}
if !cmp.need_split() {
for x in &mut open_files {
x.do_split(false);
}
}
// FIXME -- Check Header
if open_files[0].has_header() {
w.write_all(open_files[0].header().line.as_bytes())?;
}
let nums: Vec<usize> = (0..open_files.len()).collect();
let mut mm = MergeTreeItem::new_tree(&open_files, &nums);
if unique {
let x = mm.next(cmp, &mut open_files)?;
if x.is_none() {
return Ok(());
}
let x = x.unwrap();
w.write_all(open_files[x].curr_line().line())?;
let mut prev = open_files[x].curr_line().clone();
loop {
let x = mm.next(cmp, &mut open_files)?;
if x.is_none() {
break;
}
let x = x.unwrap();
if !cmp.equal_cols(&prev, open_files[x].curr_line()) {
w.write_all(open_files[x].curr_line().line())?;
}
prev.assign(open_files[x].curr_line());
}
} else {
loop {
let x = mm.next(cmp, &mut open_files)?;
if x.is_none() {
break;
}
let x = x.unwrap();
w.write_all(open_files[x].curr_line().line())?;
}
}
Ok(())
}
More examples
155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293
pub fn main(argv: &[String], settings: &mut Settings) -> Result<()> {
let prog = args::ProgSpec::new("Select uniq lines.", args::FileCount::One);
const A: [ArgSpec; 7] = [
arg! {"agg", "a", "Col,Spec", "Merge value from this column, in place."},
arg! {"agg-pre", "", "NewCol,SrcCol,Spec", "Merge value from SrcCol into new column, before other columns."},
arg! {"agg-post", "", "NewCol,SrcCol,Spec", "Merge value from SrcCol into new column, after other columns."},
arg! {"key", "k", "Spec", "How to compare adjacent lines"},
arg! {"count", "c", "ColName,Position", "Write the count of matching line."},
arg! {"which", "w", "(First,Last,Min,Max)[,LineCompare]", "Which of the matching lines should be printed."},
arg! {"agg-help", "", "", "Print help for aggregators"},
];
let (args, files) = args::parse(&prog, &A, argv, settings)?;
let mut agg = LineAggList::new();
let mut comp = LineCompList::new();
let mut count = Count::default();
for x in args {
if x.name == "key" {
comp.add(&x.value)?;
} else if x.name == "count" {
count.get_count(&x.value)?;
} else if x.name == "which" {
count.get_which(&x.value)?;
} else if x.name == "agg" {
agg.push_replace(&x.value)?;
} else if x.name == "agg-post" {
agg.push_append(&x.value)?;
} else if x.name == "agg-pre" {
agg.push_prefix(&x.value)?;
} else {
unreachable!();
}
}
assert_eq!(files.len(), 1);
let mut f = Reader::new(&settings.text_in);
f.open(&files[0])?;
if f.is_empty() {
return Ok(());
}
comp.lookup(&f.names())?;
count.lookup(&f.names())?;
let mut c_write = Writer::new(settings.text_out());
if !agg.is_empty() {
if count.pos == CountPos::Begin {
agg.push_first_prefix(&format!("{},1,count", count.name))?;
}
if count.pos == CountPos::End {
agg.push_append(&format!("{},1,count", count.name))?;
}
agg.lookup(&f.names())?;
agg.fill(&mut c_write, f.header());
c_write.lookup(&f.names())?;
}
let mut w = get_writer("-")?;
if f.has_header() {
let mut ch = ColumnHeader::new();
if agg.is_empty() {
if count.pos == CountPos::Begin {
ch.push(&count.name)?;
}
ch.push_all(f.header())?;
if count.pos == CountPos::End {
ch.push(&count.name)?;
}
} else {
c_write.add_names(&mut ch, f.header())?;
}
w.write_all(ch.get_head(&settings.text_out()).as_bytes())?;
}
if f.is_done() {
return Ok(());
}
f.do_split(comp.need_split());
let mut matches = 1;
if !agg.is_empty() {
agg.add(f.curr_line());
let mut tmp = f.curr_line().clone();
loop {
if f.getline()? {
c_write.write(&mut w.0, &tmp)?;
break;
}
if comp.equal_cols(f.prev_line(1), f.curr_line()) {
count.assign(&mut tmp, f.curr_line());
agg.add(f.curr_line());
} else {
c_write.write(&mut w.0, &tmp)?;
tmp.assign(f.curr_line());
agg.reset();
agg.add(f.curr_line());
}
}
} else if count.which == Which::Last {
loop {
if f.getline()? {
count.write(&mut w.0, matches, f.prev_line(1).line(), f.delim())?;
break;
}
if comp.equal_cols(f.prev_line(1), f.curr_line()) {
matches += 1;
} else {
count.write(&mut w.0, matches, f.prev_line(1).line(), f.delim())?;
matches = 1;
}
}
} else if count.which == Which::First && count.is_plain() {
f.write_curr(&mut w.0)?;
loop {
if f.getline()? {
break;
}
if !comp.equal_cols(f.prev_line(1), f.curr_line()) {
f.write_curr(&mut w.0)?;
}
}
} else {
let mut tmp = f.curr_line().clone();
loop {
if f.getline()? {
count.write(&mut w.0, matches, tmp.line(), f.delim())?;
break;
}
if comp.equal_cols(f.prev_line(1), f.curr_line()) {
count.assign(&mut tmp, f.curr_line());
matches += 1;
} else {
count.write(&mut w.0, matches, tmp.line(), f.delim())?;
tmp.assign(f.curr_line());
matches = 1;
}
}
}
Ok(())
}
sourcepub fn fill_cache_cols(&mut self, item: &mut Item, value: &TextLine)
pub fn fill_cache_cols(&mut self, item: &mut Item, value: &TextLine)
fill Item’s cache
sourcepub fn fill_cache_line(&mut self, item: &mut Item, value: &[u8])
pub fn fill_cache_line(&mut self, item: &mut Item, value: &[u8])
fill Item’s cache
Examples found in repository?
431 432 433 434 435 436 437 438 439 440 441 442 443 444 445
fn calc(&mut self) {
self.ptrs.clear();
let mut item = Item::new();
let mut off: usize = 0;
for iter in self.data[0..self.data_used].iter().enumerate() {
if iter.1 == &b'\n' {
item.offset = off as u32;
item.size_plus = (iter.0 - off + 1) as u32;
off = iter.0 + 1;
self.cmp.fill_cache_line(&mut item, &self.data);
self.ptrs.push(item);
}
}
self.data_calc = off;
}
sourcepub fn get_value(&self) -> &[u8]ⓘNotable traits for &'_ [u8]impl<'_> Read for &'_ [u8]impl<'_> Write for &'_ mut [u8]
pub fn get_value(&self) -> &[u8]ⓘNotable traits for &'_ [u8]impl<'_> Read for &'_ [u8]impl<'_> Write for &'_ mut [u8]
get the value previously set
Examples found in repository?
2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029
pub fn line_ok_verbose(
&self,
line: &TextLine,
comp: &mut LineCompList,
line_num: usize,
) -> bool {
if !self.invert().line_ok(line, comp) {
eprint!("Line {} : ", line_num);
prerr_n(&[&line.line]);
eprint!("should have been {:?} ", self);
prerr_n(&[comp.get_value()]);
eprintln!(" but wasn't");
false
} else {
true
}
}
sourcepub fn set(&mut self, value: &[u8], delim: u8) -> Result<()>
pub fn set(&mut self, value: &[u8], delim: u8) -> Result<()>
set value fo later comparison
Examples found in repository?
2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214
pub fn line_ok_verbose(
&self,
line: &TextLine,
comp: &mut LineCompList,
line_num: usize,
) -> Result<bool> {
comp.set(self.val.as_bytes(), b',')?;
Ok(self.op.line_ok_verbose(line, comp, line_num))
}
/// compare line OP text, return true if match
pub fn line_ok(&self, line: &TextLine, comp: &mut LineCompList) -> Result<bool> {
comp.set(self.val.as_bytes(), b',')?;
let ret = self.op.line_ok(line, comp);
if !ret {
return Ok(false);
}
match self.op2 {
None => Ok(true),
Some(o) => {
comp.set(self.val2.as_ref().unwrap().as_bytes(), b',')?;
Ok(o.line_ok(line, comp))
}
}
}
More examples
89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184
pub fn main(argv: &[String], settings: &mut Settings) -> Result<()> {
let prog = args::ProgSpec::new("Search sorted files.", args::FileCount::Many);
const A: [ArgSpec; 5] = [
arg! {"key", "k", "Spec", "How to compare value to lines"},
arg! {"filename", "H", "ColName:Parts", "Prefix output lines with file name."},
arg! {"context", "C", "before,after", "print lines of context around matches"},
arg! {"sub-delim", "s", "Char", "Delimiter between keys for multi-column searches"},
arg_pos! {"pattern", "search string", "Search for this string in each file"},
];
let (args, files) = args::parse(&prog, &A, argv, settings)?;
let mut filename: Option<FileNameColumn> = None;
let mut context = Context::new();
let mut subdelim = b',';
let mut comp = LineCompList::new();
let mut pattern: Option<String> = None;
for x in args {
if x.name == "key" {
comp.add(&x.value)?;
} else if x.name == "filename" {
if filename.is_some() {
return err!("You cant use --filename twice");
}
let mut f = FileNameColumn::new();
f.set(&x.value)?;
filename = Some(f);
} else if x.name == "context" {
context.set(&x.value)?;
} else if x.name == "subdelim" {
if x.value.len() != 1 {
return err!("--sub-delim value must be a single character");
}
subdelim = x.value.as_bytes()[0];
} else if x.name == "pattern" {
pattern = Some(x.value);
} else {
unreachable!();
}
}
if pattern.is_none() {
return err!("The pattern is required");
}
let pattern = pattern.unwrap();
if files.is_empty() {
return err!("At least one file is required : you can't binary search stdin.");
}
if comp.is_empty() {
comp.add("1")?;
}
comp.set(pattern.as_bytes(), subdelim)?;
let mut w = get_writer("-")?;
let mut not_header: Vec<u8> = Vec::new();
for f in &files {
let m = MemMap::new(f)?;
not_header.clear();
if m.has_header() {
if filename.is_none() {
not_header.extend(m.header());
} else {
not_header.extend(b" CDX\t");
not_header.extend(filename.as_ref().unwrap().name.as_bytes());
not_header.extend(&m.header()[4..]);
}
}
if settings.checker.check(¬_header, f)? {
w.write_all(¬_header)?;
}
comp.lookup(&m.names())?;
let (mut start, mut stop) = equal_range_n(m.get(), &mut comp);
let (before, after) = context.get(start == stop);
for _x in 0..before {
if start == 0 {
break;
}
start = find_prev(m.get(), start);
}
for _x in 0..after {
stop = find_end(m.get(), stop);
}
if filename.is_none() {
write_all_nl(&mut w.0, &m.get()[start..stop])?;
} else {
let file: &FileNameColumn = filename.as_ref().unwrap();
while start < stop {
let end = find_end(m.get(), start);
w.write_all(f.tail_path_u8(file.tail, b'/').as_bytes())?;
w.write_all(&[b'\t'])?;
write_all_nl(&mut w.0, &m.get()[start..end])?;
start = end;
}
}
}
Ok(())
}
sourcepub fn comp_self_cols(&mut self, right: &TextLine) -> Ordering
pub fn comp_self_cols(&mut self, right: &TextLine) -> Ordering
compare my value to this line
sourcepub fn equal_self_cols(&mut self, right: &TextLine) -> bool
pub fn equal_self_cols(&mut self, right: &TextLine) -> bool
compare my value to this line
sourcepub fn comp_self_line(&mut self, right: &[u8]) -> Ordering
pub fn comp_self_line(&mut self, right: &[u8]) -> Ordering
compare my value to this line
Examples found in repository?
132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197
pub fn lower_bound_n(data: &[u8], comp: &mut LineCompList) -> (usize, usize) {
let mut trapped = false; // to exit a possible infinite loop
let mut begin: usize = 0; // start of range under consideration
let mut end: usize = data.len(); // end of range under consideration
while begin < end {
// find start and stop of a line in the middle
let mut start = if trapped {
begin
} else {
find_end(data, (end + begin - 1) / 2)
};
// if we hit end of buffer, back up from middle instead
let stop = if start == end {
let new_stop = start;
start = find_start(data, (end + begin - 1) / 2);
new_stop
} else {
find_end(data, start)
};
// data[start..stop] is one whole line, roughly in the middle of data[begin..end]
match comp.comp_self_line(&data[start..stop]) {
Ordering::Equal => {
if start == begin {
return (start, stop);
}
trapped = stop == end;
end = stop;
}
Ordering::Less => {
end = start;
}
Ordering::Greater => {
begin = stop;
}
};
}
(begin, end)
}
/// return start of first line that is greater than comp
pub fn upper_bound_n(data: &[u8], comp: &mut LineCompList) -> usize {
let mut begin: usize = 0; // start of range under consideration
let mut end: usize = data.len(); // end of range under consideration
while begin < end {
// find start and stop of a line in the middle
let mut start = find_end(data, (end + begin - 1) / 2);
// if we hit end of buffer, back up from middle instead
let stop = if start == end {
let new_stop = start;
start = find_start(data, (end + begin - 1) / 2);
new_stop
} else {
find_end(data, start)
};
// data[start..stop] is one whole line, roughly in the middle of data
if comp.comp_self_line(&data[start..stop]) == Ordering::Less {
end = start;
} else {
begin = stop;
}
}
debug_assert!(begin == end);
begin
}
Trait Implementations
sourceimpl Debug for LineCompList
impl Debug for LineCompList
sourceimpl Default for LineCompList
impl Default for LineCompList
sourcefn default() -> LineCompList
fn default() -> LineCompList
Returns the “default value” for a type. Read more
Auto Trait Implementations
impl !RefUnwindSafe for LineCompList
impl !Send for LineCompList
impl !Sync for LineCompList
impl Unpin for LineCompList
impl !UnwindSafe for LineCompList
Blanket Implementations
sourceimpl<T> BorrowMut<T> for T where
T: ?Sized,
impl<T> BorrowMut<T> for T where
T: ?Sized,
const: unstable · sourcefn borrow_mut(&mut self) -> &mut T
fn borrow_mut(&mut self) -> &mut T
Mutably borrows from an owned value. Read more
sourceimpl<T> Instrument for T
impl<T> Instrument for T
sourcefn instrument(self, span: Span) -> Instrumented<Self>
fn instrument(self, span: Span) -> Instrumented<Self>
sourcefn in_current_span(self) -> Instrumented<Self>
fn in_current_span(self) -> Instrumented<Self>
impl<V, T> VZip<V> for T where
V: MultiLane<T>,
impl<V, T> VZip<V> for T where
V: MultiLane<T>,
fn vzip(self) -> V
sourceimpl<T> WithSubscriber for T
impl<T> WithSubscriber for T
sourcefn with_subscriber<S>(self, subscriber: S) -> WithDispatch<Self> where
S: Into<Dispatch>,
fn with_subscriber<S>(self, subscriber: S) -> WithDispatch<Self> where
S: Into<Dispatch>,
Attaches the provided Subscriber
to this type, returning a
WithDispatch
wrapper. Read more
sourcefn with_current_subscriber(self) -> WithDispatch<Self>
fn with_current_subscriber(self) -> WithDispatch<Self>
Attaches the current default Subscriber
to this type, returning a
WithDispatch
wrapper. Read more