Updates the table creation logic.

The table parsing/creation logic has changed from treating every line the same
to processing each line in context of the column header's placement. Previously,
lines on separate rows would go towards the same column as long as they were the
same index based on separator alone. Now, each item's index is based on vertical
alignment to the column header.

This may seem brittle, but it solves the problem of some tables operating with
empty cells that would cause remaining values to be paired with the wrong
column.

Based on kubernetes output (get pods, events), the new method has shown to have
much greater success rates for parsing.
This commit is contained in:
Thomas Hartmann 2019-10-17 00:20:48 +02:00
parent a0ed6ea3c8
commit 9b1ff9b566

View File

@ -46,33 +46,39 @@ fn string_to_table(
let mut lines = s.lines().filter(|l| !l.trim().is_empty());
let separator = " ".repeat(std::cmp::max(split_at, 1));
let headers = lines
.next()?
.split(&separator)
.map(|s| s.trim())
.filter(|s| !s.is_empty())
.map(|s| s.to_owned())
.collect::<Vec<String>>();
let headers_raw = lines.next()?;
let header_row = if headerless {
(1..=headers.len())
.map(|i| format!("Column{}", i))
.collect::<Vec<String>>()
} else {
let headers = headers_raw
.trim()
.split(&separator)
.map(str::trim)
.filter(|s| !s.is_empty())
.map(|s| (headers_raw.find(s).unwrap(), s.to_owned()));
let columns = if headerless {
headers
.enumerate()
.map(|(header_no, (string_index, _))| {
(string_index, format!("Column{}", header_no + 1))
})
.collect::<Vec<(usize, String)>>()
} else {
headers.collect::<Vec<(usize, String)>>()
};
Some(
lines
.map(|l| {
header_row
columns
.iter()
.zip(
l.split(&separator)
.map(|s| s.trim())
.filter(|s| !s.is_empty()),
)
.map(|(a, b)| (String::from(a), String::from(b)))
.enumerate()
.filter_map(|(i, (start, col))| {
(match columns.get(i + 1) {
Some((end, _)) => l.get(*start..*end),
None => l.get(*start..)?.split(&separator).next(),
})
.and_then(|s| Some((col.clone(), String::from(s.trim()))))
})
.collect()
})
.collect(),