Skip to content

Fix/time #500

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
MartinKl merged 13 commits into from
Jan 15, 2026
Merged

Fix/time #500

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
13 commits
Select commit Hold shift + click to select a range
8e8fb63
allow newpar and newdoc keywords
MartinKl Jan 15, 2026
6721fb1
generalize functionality
MartinKl Jan 15, 2026
344b097
fix by-value tracker, values were tracked the wrong way which could h…
MartinKl Jan 15, 2026
b3772e9
update
MartinKl Jan 15, 2026
1d0b1e7
overwrite existing annotations
MartinKl Jan 15, 2026
b856146
update
MartinKl Jan 15, 2026
62649ea
build update at the end to avoid misleading error messages
MartinKl Jan 15, 2026
28f7cb1
update
MartinKl Jan 15, 2026
76aa93a
fixed time module
MartinKl Jan 15, 2026
bdfa910
new test
MartinKl Jan 15, 2026
6af28f3
numeric as orderedfloat
MartinKl Jan 15, 2026
54411ef
update
MartinKl Jan 15, 2026
859dc22
Format Rust code using rustfmt
github-actions[bot] Jan 15, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
15 changes: 15 additions & 0 deletions CHANGELOG.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -5,6 +5,21 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0

## [Unreleased]

### Added

- import `conllu`: Allow `newpar` and `newdoc` keywords

### Changed

- `enumerate`: sort as numeric uses float internally (lower maximum value, but sorting time values is possible)
- `time`: More generic functionality
- `time`: existing time annotations are now overwritten

### Fixed

- `enumerate`: Fixed tracking of `by`-values
- `time`: no more misleading error messages

## [0.46.0] - 2026-01-13

### Added
Expand Down
5 changes: 4 additions & 1 deletion src/importer/conllu/conllu.pest
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -3,11 +3,14 @@ whitespace = _{ "\t" }
initial_padding = _{ SOI ~ (NEWLINE*)? }
final_padding = _{ (NEWLINE*)? ~ EOI }
conllu = ${ initial_padding ~ sentence+ ~ final_padding }
sentence = ${ ( s_anno | s_comment )* ~ (multi_token | empty_node | token)+ ~ NEWLINE? }
sentence = ${ ( text_structure | s_anno | s_comment )* ~ (multi_token | empty_node | token)+ ~ NEWLINE? }
s_anno = ${ hash ~ space* ~ name ~ space* ~ equals ~ space* ~ s_anno_value ~ NEWLINE }
s_anno_value = @{ (char | WHITESPACE )+ }
s_comment = ${ hash ~ space* ~ comment ~ NEWLINE }
comment = @{ comment_char+ }
text_structure = { hash ~ space* ~ (newdoc | newpar) ~ NEWLINE }
newdoc = { "newdoc" ~ (char | space)* }
newpar = { "newpar" }

token = ${ id ~ whitespace
~ ( no_value | form ) ~ whitespace
Expand Down
26 changes: 15 additions & 11 deletions src/manipulator/enumerate.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -13,6 +13,7 @@ use graphannis_core::{
graph::{ANNIS_NS, NODE_NAME_KEY, NODE_TYPE_KEY},
};
use itertools::Itertools;
use ordered_float::OrderedFloat;
use serde::Serialize;
use serde_derive::Deserialize;

Expand Down Expand Up @@ -126,15 +127,17 @@ impl<'a> SortByNode {
fn sortable_value(&self, value: Cow<'a, str>) -> Result<SortValue<'a>, anyhow::Error> {
Ok(match self {
SortByNode::AsString(_) => SortValue::StringValue(value),
SortByNode::AsInteger { .. } => SortValue::NumericValue(value.parse::<usize>()?),
SortByNode::AsInteger { .. } => {
SortValue::NumericValue(value.parse::<OrderedFloat<f64>>()?)
}
})
}
}

#[derive(PartialEq, PartialOrd, Eq, Ord)]
enum SortValue<'a> {
StringValue(Cow<'a, str>),
NumericValue(usize),
NumericValue(OrderedFloat<f64>),
}

impl Default for EnumerateMatches {
Expand Down Expand Up @@ -174,11 +177,9 @@ impl Manipulator for EnumerateMatches {

for query_s in &self.queries {
let query = aql::parse(query_s, false)?;
let mut search_results: Vec<_> = Vec::new();
for m in aql::execute_query_on_graph(graph, &query, true, None)? {
let m = m?;
search_results.push(m);
}
let mut search_results = aql::execute_query_on_graph(graph, &query, true, None)?
.flatten()
.collect_vec();
// Sort results with the default ANNIS sort order
search_results.sort_by(|m1, m2| {
sort_cache
Expand Down Expand Up @@ -230,9 +231,10 @@ impl Manipulator for EnumerateMatches {
let mut offset = 0;
let mut i_correction = 0;
let mut visited = BTreeSet::new();
let mut by_values = Vec::with_capacity(self.by.len());
let mut by_values = vec![String::with_capacity(0); self.by.len()];
let mut reset_count;
for (i, mut m) in search_results.into_iter().enumerate() {
let mut reset_count = false;
reset_count = false;
let matching_nodes: Result<Vec<String>, GraphAnnisCoreError> = m
.iter()
.map(|m| {
Expand All @@ -257,17 +259,19 @@ impl Manipulator for EnumerateMatches {
.get_value_for_item(&internal_id, &coord_anno_key)?
.unwrap_or_default()
.to_string();
if let Some(previous_value) = by_values.get(bi)
if let Some(previous_value) = by_values.get_mut(bi)
&& &next_value != previous_value
{
// reset count
reset_count = true;
previous_value.clear();
previous_value.push_str(&next_value);
}
by_values.insert(bi, next_value);
}
}
if reset_count {
i_correction = i;
offset = 0;
}
if let Some(value_i) = self.value {
if value_i <= m.len() {
Expand Down
111 changes: 111 additions & 0 deletions src/manipulator/snapshots/annatto__manipulator__time__tests__fill_gaps.snap
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,111 @@
---
source: src/manipulator/time.rs
expression: "format!(\"{data_output}\\n{messages}\")"
---
---- corpus.graphml:
<?xml version="1.0" encoding="UTF-8"?>
<graphml>
<key id="k0" for="graph" attr.name="configuration" attr.type="string"/>
<key id="k1" for="node" attr.name="annis::node_type" attr.type="string"/>
<key id="k2" for="node" attr.name="annis::time" attr.type="string"/>
<key id="k3" for="node" attr.name="annis::tok" attr.type="string"/>
<graph edgedefault="directed" parse.order="nodesfirst" parse.nodeids="free" parse.edgeids="canonical">
<data key="k0"><![CDATA[
# configure visualizations here
]]></data>
<node id="corpus">
<data key="k1">corpus</data>
</node>
<node id="corpus/doc">
<data key="k1">corpus</data>
</node>
<node id="corpus/doc#t0">
<data key="k1">node</data>
<data key="k2">0.0000000000000000-0.7500000000000000</data>
<data key="k3">This</data>
</node>
<node id="corpus/doc#t1">
<data key="k1">node</data>
<data key="k2">0.7500000000000000-1.5000000000000000</data>
<data key="k3">is</data>
</node>
<node id="corpus/doc#t2">
<data key="k1">node</data>
<data key="k2">1.5000000000000000-2.2500000000000000</data>
<data key="k3">a</data>
</node>
<node id="corpus/doc#t3">
<data key="k1">node</data>
<data key="k2">2.2500000000000000-3.0000000000000000</data>
<data key="k3">test</data>
</node>
<node id="corpus/doc#t4">
<data key="k1">node</data>
<data key="k2">4.0000000000000000-5.3333333333333330</data>
<data key="k3">What</data>
</node>
<node id="corpus/doc#t5">
<data key="k1">node</data>
<data key="k2">5.3333333333333330-6.6666666666666661</data>
<data key="k3">will</data>
</node>
<node id="corpus/doc#t6">
<data key="k1">node</data>
<data key="k2">6.6666666666666661-8.0000000000000000</data>
<data key="k3">happen</data>
</node>
<node id="corpus/doc#t7">
<data key="k1">node</data>
<data key="k2">20.0000000000000000-22.0000000000000000</data>
<data key="k3">nothing</data>
</node>
<node id="corpus/doc#t8">
<data key="k1">node</data>
<data key="k2">27.0000000000000000-28.5000000000000000</data>
<data key="k3">sure</data>
</node>
<node id="corpus/doc#t9">
<data key="k1">node</data>
<data key="k2">28.5000000000000000-30.0000000000000000</data>
<data key="k3">thing</data>
</node>
<edge id="e0" source="corpus/doc#t0" target="corpus/doc#t1" label="Ordering/annis/">
</edge>
<edge id="e1" source="corpus/doc#t1" target="corpus/doc#t2" label="Ordering/annis/">
</edge>
<edge id="e2" source="corpus/doc#t2" target="corpus/doc#t3" label="Ordering/annis/">
</edge>
<edge id="e3" source="corpus/doc#t3" target="corpus/doc#t4" label="Ordering/annis/">
</edge>
<edge id="e4" source="corpus/doc#t4" target="corpus/doc#t5" label="Ordering/annis/">
</edge>
<edge id="e5" source="corpus/doc#t5" target="corpus/doc#t6" label="Ordering/annis/">
</edge>
<edge id="e6" source="corpus/doc#t6" target="corpus/doc#t7" label="Ordering/annis/">
</edge>
<edge id="e7" source="corpus/doc#t7" target="corpus/doc#t8" label="Ordering/annis/">
</edge>
<edge id="e8" source="corpus/doc#t8" target="corpus/doc#t9" label="Ordering/annis/">
</edge>
<edge id="e9" source="corpus/doc#t0" target="corpus/doc" label="PartOf/annis/">
</edge>
<edge id="e10" source="corpus/doc#t1" target="corpus/doc" label="PartOf/annis/">
</edge>
<edge id="e11" source="corpus/doc#t2" target="corpus/doc" label="PartOf/annis/">
</edge>
<edge id="e12" source="corpus/doc#t3" target="corpus/doc" label="PartOf/annis/">
</edge>
<edge id="e13" source="corpus/doc#t4" target="corpus/doc" label="PartOf/annis/">
</edge>
<edge id="e14" source="corpus/doc#t5" target="corpus/doc" label="PartOf/annis/">
</edge>
<edge id="e15" source="corpus/doc#t6" target="corpus/doc" label="PartOf/annis/">
</edge>
<edge id="e16" source="corpus/doc#t7" target="corpus/doc" label="PartOf/annis/">
</edge>
<edge id="e17" source="corpus/doc#t8" target="corpus/doc" label="PartOf/annis/">
</edge>
<edge id="e18" source="corpus/doc#t9" target="corpus/doc" label="PartOf/annis/">
</edge>
</graph>
</graphml>
8 changes: 4 additions & 4 deletions src/manipulator/snapshots/annatto__manipulator__time__tests__sparse_to_full_pass.snap
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -109,15 +109,15 @@ expression: actual.unwrap()
<node id="valid-sparse-timevalues_2/import/exmaralda/test_doc#t_dipl_T3-T4">
<data key="k11">dipl</data>
<data key="k13">node</data>
<data key="k19">4.44444-5.55555</data>
<data key="k19">4.4444400000000002-5.5555500000000002</data>
<data key="k20">York</data>
<data key="k5">York</data>
</node>
<node id="valid-sparse-timevalues_2/import/exmaralda/test_doc#t_norm_T286-T0">
<data key="k11">norm</data>
<data key="k13">node</data>
<data key="k14">I</data>
<data key="k19">0-1</data>
<data key="k19">0.0000000000000000-1.0000000000000000</data>
<data key="k20">I</data>
</node>
<node id="valid-sparse-timevalues_2/import/exmaralda/test_doc#t_norm_T0-T1">
Expand Down Expand Up @@ -145,14 +145,14 @@ expression: actual.unwrap()
<data key="k11">dipl</data>
<data key="k13">node</data>
<data key="k18">1</data>
<data key="k19">0-5.55555</data>
<data key="k19">0.0000000000000000-5.5555500000000002</data>
</node>
<node id="valid-sparse-timevalues_2/import/exmaralda/test_doc#a_norm_T286-T0">
<data key="k11">norm</data>
<data key="k12">I</data>
<data key="k13">node</data>
<data key="k17">PRON</data>
<data key="k19">0-1</data>
<data key="k19">0.0000000000000000-1.0000000000000000</data>
</node>
<node id="valid-sparse-timevalues_2/import/exmaralda/test_doc#a_norm_T0-T1">
<data key="k11">norm</data>
Expand Down
Loading