Struct cdx::TextLine [−][src]
Expand description
A line of a text file, broken into fields.
Access to the lines and parts is allowed, but should seldom be necessary
line includes the trailing newline, but no field contains the newline
An empty line contains one empty field
use std::io::BufRead;
let mut data = b"one\ttwo\tthree\n";
let mut dp = &data[..];
let mut line = cdx::TextLine::new();
let eof = line.read(&mut dp).unwrap();
assert_eq!(eof, false);
assert_eq!(line.strlen(), 14);
line.split(b'\t');
assert_eq!(line.len(), 3);
assert_eq!(line.get(1), b"two");Fields
line: Vec<u8>The whole input line, with newline
parts: Vec<FakeSlice>the individual columns
Implementations
make a new TextLine
Examples found in repository
src/lib.rs (line 601)
≺ ≻
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
pub fn new() -> Self {
Self {
file: Infile::default(),
line: TextLine::new(),
cont: InfileContext::new(),
do_split: true,
}
}
/// get current line
pub fn curr(&self) -> &TextLine {
&self.line
}
/// get header
pub fn header(&self) -> &StringLine {
&self.cont.header
}
/// get column names
pub fn names(&self) -> Vec<&str> {
self.cont.header.vec()
}
/// open file for reading
pub fn open(&mut self, name: &str) -> Result<()> {
self.file = get_reader(name)?;
self.cont.read_header(&mut *self.file, &mut self.line)
}
/// was the file zero bytes?
pub fn is_empty(&self) -> bool {
self.cont.is_empty
}
/// have we read all the lines?
pub fn is_done(&self) -> bool {
self.cont.is_done
}
/// write the current text line with newline
pub fn write(&self, w: &mut impl Write) -> Result<()> {
w.write_all(&self.line.line)?;
Ok(())
}
/// get the next line of text. Return true if no more data available.
pub fn getline(&mut self) -> Result<bool> {
if !self.cont.is_done {
if self.line.read(&mut *self.file)? {
self.cont.is_done = true;
} else if self.do_split {
self.line.split(self.cont.delim);
}
}
Ok(self.cont.is_done)
}
}
#[derive(Debug, Default)]
/// File reader for text file broken into lines with columns
/// previous N lines are stil available
pub struct LookbackReader {
file: Infile,
lines: Vec<TextLine>,
cont: InfileContext,
/// Automatically split each line into columns
pub do_split: bool,
curr: usize,
}
impl LookbackReader {
/// make a new LookbackReader
pub fn new(lookback: usize) -> Self {
let mut lines: Vec<TextLine> = Vec::new();
lines.resize(lookback + 1, TextLine::new());
Self {
file: Infile::default(),
lines,
cont: InfileContext::new(),
do_split: true,
curr: 0,
}
}More examples
pub fn iter(&self) -> TextLineIter<'_>ⓘNotable traits for TextLineIter<'a>impl<'a> Iterator for TextLineIter<'a> type Item = &'a [u8];
pub fn iter(&self) -> TextLineIter<'_>ⓘNotable traits for TextLineIter<'a>impl<'a> Iterator for TextLineIter<'a> type Item = &'a [u8];
Notable traits for TextLineIter<'a>
impl<'a> Iterator for TextLineIter<'a> type Item = &'a [u8];Iterator over columns in the line
How many column in the line
Examples found in repository
src/lib.rs (line 403)
≺ ≻
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
fn next(&mut self) -> Option<Self::Item> {
if self.index >= self.line.len() {
None
} else {
self.index += 1;
Some(&self.line[self.index - 1])
}
}
}
impl<'a> Iterator for StringLineIter<'a> {
// we will be counting with usize
type Item = &'a str;
fn next(&mut self) -> Option<Self::Item> {
if self.index >= self.line.len() {
None
} else {
self.index += 1;
Some(&self.line[self.index - 1])
}
}
}
/// Input file. Wrapped in a type so I can 'impl Debug'
pub struct Infile(
/// The file being read
io::BufReader<Box<dyn Read>>,
);
impl Infile {
/// create a new input file
pub fn new(f: io::BufReader<Box<dyn Read>>) -> Self {
Self(f)
}
}
impl Default for Infile {
fn default() -> Self {
Self::new(io::BufReader::new(Box::new(io::empty())))
}
}
impl fmt::Debug for Infile {
fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {
write!(f, "Infile")
}
}
impl Deref for Infile {
type Target = io::BufReader<Box<dyn Read>>;
fn deref(&self) -> &Self::Target {
&self.0
}
}
impl DerefMut for Infile {
fn deref_mut(&mut self) -> &mut Self::Target {
&mut self.0
}
}
type Outfile = io::BufWriter<Box<dyn Write>>;
/// Make an Outfile from a file name
pub fn get_writer(name: &str) -> Result<Outfile> {
let inner: Box<dyn Write> = {
if name == "-" {
Box::new(io::stdout())
} else if name == "--" {
Box::new(io::stderr())
} else {
Box::new(fs::OpenOptions::new().write(true).create(true).open(name)?)
}
};
Ok(io::BufWriter::new(inner))
}
fn unescape_vec(data: &[u8]) -> Vec<u8> {
let mut ret: Vec<u8> = Vec::with_capacity(data.len());
let mut last_was_slash = false;
for x in data {
if last_was_slash {
ret.push(match x {
b'n' => b'\n',
b't' => b'\t',
b's' => b' ',
ch => *ch,
});
last_was_slash = false;
} else if x == &b'\\' {
last_was_slash = true;
} else {
ret.push(*x);
}
}
if last_was_slash {
ret.push(b'\\');
}
ret
}
/// Make an Infile from a file name
pub fn get_reader(name: &str) -> Result<Infile> {
let inner: Box<dyn Read> = {
if name == "-" {
// unsafe { Box::new(std::fs::File::from_raw_fd(1)) }
Box::new(io::stdin())
// } else if name.starts_with("s3://") {
// Box::new(open_s3_file(name)?)
} else if let Some(stripped) = name.strip_prefix("<<") {
Box::new(std::io::Cursor::new(unescape_vec(stripped.as_bytes())))
} else {
Box::new(fs::File::open(name)?)
}
};
let mut outer = io::BufReader::new(inner);
let start = outer.fill_buf()?;
if start.starts_with(&[0x1fu8, 0x8bu8, 0x08u8]) {
outer = io::BufReader::new(Box::new(MultiGzDecoder::new(outer)));
}
Ok(Infile::new(outer))
}
#[derive(Debug, Default)]
struct InfileContext {
header: StringLine,
delim: u8,
is_done: bool,
is_empty: bool,
}
// FIXME -- specify delimiter
// if CDX and specified and different, then strip header
/// Reader header line, if any, and first line of text
impl InfileContext {
fn new() -> Self {
Self {
header: StringLine::new(),
delim: b'\t',
is_done: true,
is_empty: true,
}
}
fn read_header(&mut self, file: &mut impl BufRead, line: &mut TextLine) -> Result<()> {
if self.header.read(file)? {
self.is_done = true;
self.is_empty = true;
return Ok(());
}
self.is_done = false;
self.is_empty = false;
if self.header.line.starts_with(" CDX") {
self.delim = self.header.line.as_bytes()[4];
self.header.split(self.delim);
self.header.parts.remove(0);
if line.read(file)? {
self.is_done = true;
return Ok(());
}
line.split(self.delim);
} else {
self.delim = b'\t';
line.line = self.header.line.as_bytes().to_vec();
line.split(self.delim);
let mut head_str = String::new();
for i in 1..=line.len() {
head_str += "c";
head_str += &i.to_string();
head_str += "\t";
}
head_str.pop();
head_str += "\n";
let mut fake_head = head_str.as_bytes();
self.header.read(&mut fake_head)?;
self.header.split(self.delim);
self.header.line.clear();
}
Ok(())
}Get one column. Return an empty column if index is too big.
Examples found in repository
More examples
src/comp.rs (line 444)
≺ ≻
442 443 444 445 446 447 448 449 450 451 452 453 454
fn comp_cols(&self, spec: &Comparator, left: &TextLine, right: &TextLine) -> Ordering {
spec.mode.do_reverse(self.comp(
left.get(spec.mode.left_col.num),
right.get(spec.mode.right_col.num),
))
}
/// Compare two columns for equality
fn equal_cols(&self, spec: &Comparator, left: &TextLine, right: &TextLine) -> bool {
self.equal(
left.get(spec.mode.left_col.num),
right.get(spec.mode.right_col.num),
)
}src/column.rs (line 614)
≺ ≻
603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184
pub fn write2(&self, w: &mut dyn Write, cols: &TextLine, delim: u8) -> Result<()> {
if !self.did_lookup {
return Err(Error::NeedLookup);
}
let mut iter = self.columns.iter();
match iter.next() {
None => {}
Some(first) => {
w.write_all(&cols[first.num])?;
for x in iter {
w.write_all(&[delim])?;
w.write_all(cols.get(x.num))?;
}
}
};
w.write_all(&[b'\n'])?;
Ok(())
}
/// write the appropriate selection from the given columns, but no trailing newline
pub fn write3(&self, w: &mut dyn Write, cols: &TextLine, delim: u8) -> Result<()> {
if !self.did_lookup {
return Err(Error::NeedLookup);
}
let mut iter = self.columns.iter();
match iter.next() {
None => {}
Some(first) => {
w.write_all(cols.get(first.num))?;
for x in iter {
w.write_all(&[delim])?;
w.write_all(cols.get(x.num))?;
}
}
};
Ok(())
}
/// write the appropriate selection from the given columns, but no trailing newline
pub fn write3s(&self, w: &mut dyn Write, cols: &StringLine, delim: u8) -> Result<()> {
if !self.did_lookup {
return Err(Error::NeedLookup);
}
let mut iter = self.columns.iter();
match iter.next() {
None => {}
Some(first) => {
w.write_all(cols.get(first.num).as_bytes())?;
for x in iter {
w.write_all(&[delim])?;
w.write_all(cols.get(x.num).as_bytes())?;
}
}
};
Ok(())
}
/// write the appropriate selection from the given columns, but no trailing newline
/// trying to write a non-existant column writes the provided default value
pub fn write_sloppy(&self, cols: &[&str], rest: &str, w: &mut dyn Write) -> Result<()> {
if !self.did_lookup {
return Err(Error::NeedLookup);
}
for x in &self.columns {
if x.num < cols.len() {
w.write_all(cols[x.num].as_bytes())?;
} else {
w.write_all(rest.as_bytes())?;
}
}
Ok(())
}
/// Select columns from input line based on `ColumnSet`, fill in default if line is too short """
/// # Examples
///
/// ```
/// use cdx::column::ColumnSet;
/// let header: [&str; 5] = ["zero", "one", "two", "three", "four"];
/// let mut s = ColumnSet::new();
/// s.add_no("two");
/// s.lookup(&header);
/// let v = ["Zeroth", "First", "Second", "Third"];
/// let mut res = Vec::new();
/// s.select_sloppy(&v, &"extra", &mut res);
/// assert_eq!(res, vec!["Zeroth", "First", "Third", "extra"]);
/// ```
pub fn select_sloppy<T: AsRef<str> + Clone>(
&self,
cols: &[T],
restval: &T,
result: &mut Vec<T>,
) -> Result<()> {
if !self.did_lookup {
return Err(Error::NeedLookup);
}
result.clear();
for x in &self.columns {
if x.num < cols.len() {
result.push(cols[x.num].clone());
} else {
result.push(restval.clone());
}
}
Ok(())
}
/// return owned columns by const reference
pub fn get_cols(&self) -> &Vec<OutCol> {
&self.columns
}
/// steal owned columns by value
pub fn get_cols_full(self) -> Vec<OutCol> {
self.columns
}
/// get owned column numbers
pub fn get_cols_num(&self) -> Vec<usize> {
let mut v = Vec::with_capacity(self.columns.len());
for x in &self.columns {
v.push(x.num);
}
v
}
/// Shorthand to look up some columns
/// # Examples
///
/// ```
/// use cdx::column::ColumnSet;
/// let header: [&str; 5] = ["zero", "one", "two", "three", "four"];
/// assert_eq!(ColumnSet::lookup_cols("~2-3", &header).unwrap(), &[0,3,4]);
/// ```
pub fn lookup_cols(spec: &str, names: &[&str]) -> Result<Vec<usize>> {
let mut s = ColumnSet::new();
s.add_yes(spec);
s.lookup(names)?;
Ok(s.get_cols_num())
}
/// Shorthand to look up some columns, with names
pub fn lookup_cols_full(spec: &str, names: &[&str]) -> Result<Vec<OutCol>> {
let mut s = ColumnSet::new();
s.add_yes(spec);
s.lookup(names)?;
Ok(s.get_cols_full())
}
/// Shorthand to look up a single column
/// To look up a single named column, `lookup_col` is also available
/// # Examples
///
/// ```
/// use cdx::column::ColumnSet;
/// let header: [&str; 5] = ["zero", "one", "two", "three", "four"];
/// assert_eq!(ColumnSet::lookup1("three", &header).unwrap(), 3);
/// ```
pub fn lookup1(spec: &str, names: &[&str]) -> Result<usize> {
let mut s = ColumnSet::new();
s.add_yes(spec);
s.lookup(names)?;
if s.get_cols().len() != 1 {
return err!(
"Spec {} resolves to {} columns, rather than a single column",
spec,
s.get_cols().len()
);
}
Ok(s.get_cols_num()[0])
}
}
/*
impl ColumnFun for ReaderFull<'_> {
fn write(&self, w: &mut dyn Write, line: &TextLine, delim: u8) -> Result<()> {
let mut need_delim = false;
for x in line.iter() {
if need_delim {
w.write_all(&[delim])?;
}
need_delim = true;
w.write_all(x)?;
}
Ok(())
}
fn write_names(&self, w: &mut dyn Write, head: &StringLine, delim: u8) -> Result<()> {
let mut need_delim = false;
for x in head.iter() {
if need_delim {
w.write_all(&[delim])?;
}
need_delim = true;
w.write_all(x)?;
}
Ok(())
}
}
*/
/// Write the columns with a custom delimiter
pub struct ColumnClump<'a> {
cols: Box<dyn ColumnFun + 'a>,
name: String,
delim: u8,
}
impl fmt::Debug for ColumnClump<'_> {
fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {
write!(f, "ColumnClump")
}
}
impl<'a> ColumnClump<'a> {
/// new ColumnClump from parts
pub fn new(cols: Box<dyn ColumnFun + 'a>, name: &str, delim: u8) -> Self {
Self {
cols,
name: name.to_string(),
delim,
}
}
/// new ColumnClump from spec : DelimOutcol:Columns
/// e.g. ,group:1-3
pub fn from_spec(orig_spec: &str) -> Result<Self> {
let mut spec = orig_spec;
if spec.is_empty() {
return err!("Can't construct a group from an empty string");
}
let delim = take_first(&mut spec);
if delim.len_utf8() != 1 {
return err!("Delimiter must be a plain ascii character : {}", orig_spec);
}
let parts = spec.split_once(':');
if parts.is_none() {
return err!(
"No colon found. Group format is DelimOutname:Columns : {}",
orig_spec
);
}
let parts = parts.unwrap();
let mut g = ColumnSet::new();
g.add_yes(parts.1);
let cols = Box::new(ReaderColumns::new(g));
Ok(Self {
cols,
name: parts.0.to_string(),
delim: delim as u8,
})
}
}
impl<'a> ColumnFun for ColumnClump<'a> {
fn write(&self, w: &mut dyn Write, line: &TextLine, _delim: u8) -> Result<()> {
self.cols.write(w, line, self.delim)?;
Ok(())
}
fn write_names(&self, w: &mut dyn Write, _head: &StringLine, _delim: u8) -> Result<()> {
w.write_all(self.name.as_bytes())?;
Ok(())
}
fn lookup(&mut self, fieldnames: &[&str]) -> Result<()> {
self.cols.lookup(fieldnames)
}
}
/// Selection of columns from a Reader
#[derive(Debug)]
pub struct ReaderColumns {
columns: ColumnSet,
}
impl ReaderColumns {
/// new ReaderColumns
pub fn new(columns: ColumnSet) -> Self {
Self { columns }
}
}
/// Write column name : col.name if non empty, else head[col.num]
pub fn write_colname(w: &mut dyn Write, col: &OutCol, head: &StringLine) -> Result<()> {
if col.name.is_empty() {
w.write_all(head.get(col.num).as_bytes())?;
} else {
w.write_all(col.name.as_bytes())?;
}
Ok(())
}
impl ColumnFun for ReaderColumns {
fn write(&self, w: &mut dyn Write, line: &TextLine, delim: u8) -> Result<()> {
self.columns.write3(w, line, delim)?;
Ok(())
}
fn write_names(&self, w: &mut dyn Write, head: &StringLine, delim: u8) -> Result<()> {
let mut iter = self.columns.get_cols().iter();
match iter.next() {
None => {}
Some(first) => {
write_colname(w, first, head)?;
for x in iter {
w.write_all(&[delim])?;
write_colname(w, x, head)?;
}
}
}
// self.columns.write3s(w, head, delim)?;
Ok(())
}
fn lookup(&mut self, fieldnames: &[&str]) -> Result<()> {
self.columns.lookup(fieldnames)
}
}
/// A collection of ColumnFun writers
pub struct Writer<'a> {
v: Vec<Box<dyn ColumnFun + 'a>>,
delim: u8,
}
impl fmt::Debug for Writer<'_> {
fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {
write!(f, "Writer")
}
}
impl<'a> Writer<'a> {
/// new Writer
pub fn new(delim: u8) -> Self {
Self {
v: Vec::new(),
delim,
}
}
/// is it empty
pub fn is_empty(&self) -> bool {
self.v.is_empty()
}
/// resolve column names
pub fn lookup(&mut self, fieldnames: &[&str]) -> Result<()> {
for x in self.v.iter_mut() {
x.lookup(fieldnames)?
}
Ok(())
}
/// Add a new writer
pub fn push(&mut self, x: Box<dyn ColumnFun + 'a>) {
self.v.push(x);
}
/// Write the column names
pub fn write_names(&self, w: &mut dyn Write, head: &StringLine) -> Result<()> {
w.write_all(b" CDX")?;
for x in self.v.iter() {
w.write_all(&[self.delim])?;
x.write_names(w, head, self.delim)?;
}
w.write_all(&[b'\n'])?;
Ok(())
}
/// Write the column values
pub fn write(&self, w: &mut dyn Write, line: &TextLine) -> Result<()> {
let mut iter = self.v.iter();
match iter.next() {
None => {}
Some(first) => {
first.write(w, line, self.delim)?;
for x in iter {
w.write_all(&[self.delim])?;
x.write(w, line, self.delim)?;
}
}
};
w.write_all(&[b'\n'])?;
Ok(())
}
}
impl<'a> Default for Writer<'a> {
fn default() -> Self {
Self::new(b'\t')
}
}
/// a column, by name or number
#[derive(Debug, Clone)]
pub struct NamedCol {
/// the column name. Empty if using column by number
pub name: String,
/// the columnn number, either as originally set or after lookup
pub num: usize,
/// if non-zero, input was "+2" so num should be calculated as (num_cols - from_end)
pub from_end: usize,
}
impl NamedCol {
/// new named column
pub fn new() -> Self {
Self {
name: String::new(),
num: 0,
from_end: 0,
}
}
/// Resolve the column name
pub fn lookup(&mut self, fieldnames: &[&str]) -> Result<()> {
if !self.name.is_empty() {
self.num = ColumnSet::lookup_col(fieldnames, &self.name)?
} else if self.from_end > 0 {
if self.from_end > fieldnames.len() {
return err!(
"Requested column +{}, but there are only {} columns",
self.from_end,
fieldnames.len()
);
}
self.num = fieldnames.len() - self.from_end
}
Ok(())
}
/// Extract a column name or number, return the unused part of the slice
pub fn parse<'a>(&mut self, orig_spec: &'a str) -> Result<&'a str> {
let mut spec = orig_spec;
self.num = 0;
self.name.clear();
if spec.is_empty() {
return Ok(spec);
}
let mut ch = first(spec);
let was_plus = ch == '+';
if was_plus {
spec = skip_first(spec);
ch = first(spec);
}
if ch.is_ascii_digit() {
let mut pos: usize = 0;
for x in spec.chars() {
if x.is_ascii_digit() {
self.num = self.num * 10 + (x as usize) - ('0' as usize);
pos += 1;
} else {
break;
}
}
if was_plus {
self.from_end = self.num;
} else {
self.num -= 1;
}
Ok(&spec[pos..])
} else if ch.is_alphabetic() {
if was_plus {
return err!("'+' must be follwed by a number : {}", orig_spec);
}
let mut pos: usize = 0;
self.name.clear();
for x in spec.chars() {
if x.is_alphanumeric() || x == '_' {
self.name.push(x);
pos += 1;
} else {
break;
}
}
Ok(&spec[pos..])
} else {
err!("Bad parse of compare spec for {}", spec)
}
}
}
impl Default for NamedCol {
fn default() -> Self {
Self::new()
}
}
#[derive(Debug, Clone, Default)]
struct CompositeColumnPart {
prefix: String,
col: NamedCol,
}
impl CompositeColumnPart {
fn new() -> Self {
Self::default()
}
fn lookup(&mut self, fieldnames: &[&str]) -> Result<()> {
self.col.lookup(fieldnames)
}
}
/// Create a string from a bunch of static stings and column values
#[derive(Debug, Clone, Default)]
pub struct CompositeColumn {
parts: Vec<CompositeColumnPart>,
suffix: String,
name: String,
}
impl CompositeColumn {
/// new
pub fn new(s: &str) -> Result<Self> {
let mut c = CompositeColumn::default();
c.set(s)?;
Ok(c)
}
/// resolve named columns
pub fn lookup(&mut self, fieldnames: &[&str]) -> Result<()> {
for x in &mut self.parts {
x.lookup(fieldnames)?;
}
Ok(())
}
/// contruct string from column values
pub fn get(&self, t: &mut Vec<u8>, fields: &[&[u8]]) {
t.clear();
for x in &self.parts {
t.extend(x.prefix.as_bytes());
t.extend(fields[x.col.num]);
}
t.extend(self.suffix.as_bytes());
}
/// configure from spec
pub fn set(&mut self, spec: &str) -> Result<()> {
let name = spec.split_once(':');
if name.is_none() {
return err!("Composite Column Spec must start with ColName: : {}", spec);
}
let name = name.unwrap();
self.name = name.0.to_string();
let mut curr = name.1;
self.suffix.clear();
self.parts.clear();
const TAG: char = '^';
while !curr.is_empty() {
let ch = take_first(&mut curr);
if ch == TAG {
if curr.is_empty() {
self.suffix.push(TAG);
} else if first(curr) == TAG {
self.suffix.push(TAG);
curr = skip_first(curr);
} else {
let mut p = CompositeColumnPart::new();
std::mem::swap(&mut p.prefix, &mut self.suffix);
if first(curr) == '{' {
curr = skip_first(curr);
curr = p.col.parse(curr)?;
if curr.is_empty() || first(curr) != '}' {
return err!("Closing bracket not found : {}", spec);
}
curr = skip_first(curr);
} else {
curr = p.col.parse(curr)?;
}
self.parts.push(p);
}
} else {
self.suffix.push(ch);
}
}
Ok(())
}
}
impl ColumnFun for CompositeColumn {
/// write the column names (called once)
fn write_names(&self, w: &mut dyn Write, _head: &StringLine, _delim: u8) -> Result<()> {
w.write_all(self.name.as_bytes())?;
Ok(())
}
/// write the column values (called many times)
fn write(&self, w: &mut dyn Write, line: &TextLine, _delim: u8) -> Result<()> {
for x in &self.parts {
w.write_all(x.prefix.as_bytes())?;
w.write_all(line.get(x.col.num))?;
}
w.write_all(self.suffix.as_bytes())?;
Ok(())
}Read a new line from a file, should generally be followed by split
Examples found in repository
src/lib.rs (line 559)
≺ ≻
547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710
fn read_header(&mut self, file: &mut impl BufRead, line: &mut TextLine) -> Result<()> {
if self.header.read(file)? {
self.is_done = true;
self.is_empty = true;
return Ok(());
}
self.is_done = false;
self.is_empty = false;
if self.header.line.starts_with(" CDX") {
self.delim = self.header.line.as_bytes()[4];
self.header.split(self.delim);
self.header.parts.remove(0);
if line.read(file)? {
self.is_done = true;
return Ok(());
}
line.split(self.delim);
} else {
self.delim = b'\t';
line.line = self.header.line.as_bytes().to_vec();
line.split(self.delim);
let mut head_str = String::new();
for i in 1..=line.len() {
head_str += "c";
head_str += &i.to_string();
head_str += "\t";
}
head_str.pop();
head_str += "\n";
let mut fake_head = head_str.as_bytes();
self.header.read(&mut fake_head)?;
self.header.split(self.delim);
self.header.line.clear();
}
Ok(())
}
}
#[derive(Debug, Default)]
/// File reader for text file broken into lines with columns
pub struct Reader {
file: Infile,
/// The current line of text
pub line: TextLine,
cont: InfileContext,
/// automatically split each TextLine
pub do_split: bool,
}
impl Reader {
/// make a new Reader
pub fn new() -> Self {
Self {
file: Infile::default(),
line: TextLine::new(),
cont: InfileContext::new(),
do_split: true,
}
}
/// get current line
pub fn curr(&self) -> &TextLine {
&self.line
}
/// get header
pub fn header(&self) -> &StringLine {
&self.cont.header
}
/// get column names
pub fn names(&self) -> Vec<&str> {
self.cont.header.vec()
}
/// open file for reading
pub fn open(&mut self, name: &str) -> Result<()> {
self.file = get_reader(name)?;
self.cont.read_header(&mut *self.file, &mut self.line)
}
/// was the file zero bytes?
pub fn is_empty(&self) -> bool {
self.cont.is_empty
}
/// have we read all the lines?
pub fn is_done(&self) -> bool {
self.cont.is_done
}
/// write the current text line with newline
pub fn write(&self, w: &mut impl Write) -> Result<()> {
w.write_all(&self.line.line)?;
Ok(())
}
/// get the next line of text. Return true if no more data available.
pub fn getline(&mut self) -> Result<bool> {
if !self.cont.is_done {
if self.line.read(&mut *self.file)? {
self.cont.is_done = true;
} else if self.do_split {
self.line.split(self.cont.delim);
}
}
Ok(self.cont.is_done)
}
}
#[derive(Debug, Default)]
/// File reader for text file broken into lines with columns
/// previous N lines are stil available
pub struct LookbackReader {
file: Infile,
lines: Vec<TextLine>,
cont: InfileContext,
/// Automatically split each line into columns
pub do_split: bool,
curr: usize,
}
impl LookbackReader {
/// make a new LookbackReader
pub fn new(lookback: usize) -> Self {
let mut lines: Vec<TextLine> = Vec::new();
lines.resize(lookback + 1, TextLine::new());
Self {
file: Infile::default(),
lines,
cont: InfileContext::new(),
do_split: true,
curr: 0,
}
}
/// get column names
pub fn names(&self) -> Vec<&str> {
self.cont.header.vec()
}
/// open file for reading
pub fn open(&mut self, name: &str) -> Result<()> {
self.file = get_reader(name)?;
self.cont.read_header(&mut *self.file, &mut self.lines[0])
}
/// The full text of the header, without the trailing newline
pub fn header(&self) -> &String {
&self.cont.header.line
}
/// was file zero bytes?
pub fn is_empty(&self) -> bool {
self.cont.is_empty
}
/// have we hit EOF?
pub fn is_done(&self) -> bool {
self.cont.is_done
}
fn incr(&mut self) {
self.curr += 1;
if self.curr >= self.lines.len() {
self.curr = 0;
}
}
/// get next line of text
pub fn getline(&mut self) -> Result<bool> {
self.incr();
if self.lines[self.curr].read(&mut *self.file)? {
self.cont.is_done = true;
} else if self.do_split {
self.lines[self.curr].split(self.cont.delim);
}
Ok(self.cont.is_done)
}split the line into columns hypothetically you could split on one delimiter, do some work, then split on a different delimiter.
Examples found in repository
src/lib.rs (line 563)
≺ ≻
547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710
fn read_header(&mut self, file: &mut impl BufRead, line: &mut TextLine) -> Result<()> {
if self.header.read(file)? {
self.is_done = true;
self.is_empty = true;
return Ok(());
}
self.is_done = false;
self.is_empty = false;
if self.header.line.starts_with(" CDX") {
self.delim = self.header.line.as_bytes()[4];
self.header.split(self.delim);
self.header.parts.remove(0);
if line.read(file)? {
self.is_done = true;
return Ok(());
}
line.split(self.delim);
} else {
self.delim = b'\t';
line.line = self.header.line.as_bytes().to_vec();
line.split(self.delim);
let mut head_str = String::new();
for i in 1..=line.len() {
head_str += "c";
head_str += &i.to_string();
head_str += "\t";
}
head_str.pop();
head_str += "\n";
let mut fake_head = head_str.as_bytes();
self.header.read(&mut fake_head)?;
self.header.split(self.delim);
self.header.line.clear();
}
Ok(())
}
}
#[derive(Debug, Default)]
/// File reader for text file broken into lines with columns
pub struct Reader {
file: Infile,
/// The current line of text
pub line: TextLine,
cont: InfileContext,
/// automatically split each TextLine
pub do_split: bool,
}
impl Reader {
/// make a new Reader
pub fn new() -> Self {
Self {
file: Infile::default(),
line: TextLine::new(),
cont: InfileContext::new(),
do_split: true,
}
}
/// get current line
pub fn curr(&self) -> &TextLine {
&self.line
}
/// get header
pub fn header(&self) -> &StringLine {
&self.cont.header
}
/// get column names
pub fn names(&self) -> Vec<&str> {
self.cont.header.vec()
}
/// open file for reading
pub fn open(&mut self, name: &str) -> Result<()> {
self.file = get_reader(name)?;
self.cont.read_header(&mut *self.file, &mut self.line)
}
/// was the file zero bytes?
pub fn is_empty(&self) -> bool {
self.cont.is_empty
}
/// have we read all the lines?
pub fn is_done(&self) -> bool {
self.cont.is_done
}
/// write the current text line with newline
pub fn write(&self, w: &mut impl Write) -> Result<()> {
w.write_all(&self.line.line)?;
Ok(())
}
/// get the next line of text. Return true if no more data available.
pub fn getline(&mut self) -> Result<bool> {
if !self.cont.is_done {
if self.line.read(&mut *self.file)? {
self.cont.is_done = true;
} else if self.do_split {
self.line.split(self.cont.delim);
}
}
Ok(self.cont.is_done)
}
}
#[derive(Debug, Default)]
/// File reader for text file broken into lines with columns
/// previous N lines are stil available
pub struct LookbackReader {
file: Infile,
lines: Vec<TextLine>,
cont: InfileContext,
/// Automatically split each line into columns
pub do_split: bool,
curr: usize,
}
impl LookbackReader {
/// make a new LookbackReader
pub fn new(lookback: usize) -> Self {
let mut lines: Vec<TextLine> = Vec::new();
lines.resize(lookback + 1, TextLine::new());
Self {
file: Infile::default(),
lines,
cont: InfileContext::new(),
do_split: true,
curr: 0,
}
}
/// get column names
pub fn names(&self) -> Vec<&str> {
self.cont.header.vec()
}
/// open file for reading
pub fn open(&mut self, name: &str) -> Result<()> {
self.file = get_reader(name)?;
self.cont.read_header(&mut *self.file, &mut self.lines[0])
}
/// The full text of the header, without the trailing newline
pub fn header(&self) -> &String {
&self.cont.header.line
}
/// was file zero bytes?
pub fn is_empty(&self) -> bool {
self.cont.is_empty
}
/// have we hit EOF?
pub fn is_done(&self) -> bool {
self.cont.is_done
}
fn incr(&mut self) {
self.curr += 1;
if self.curr >= self.lines.len() {
self.curr = 0;
}
}
/// get next line of text
pub fn getline(&mut self) -> Result<bool> {
self.incr();
if self.lines[self.curr].read(&mut *self.file)? {
self.cont.is_done = true;
} else if self.do_split {
self.lines[self.curr].split(self.cont.delim);
}
Ok(self.cont.is_done)
}Trait Implementations
Auto Trait Implementations
impl RefUnwindSafe for TextLine
impl UnwindSafe for TextLine
Blanket Implementations
Mutably borrows from an owned value. Read more