Merge pull request #292 from korpling/feature/saltxml-exporter

Add SaltXml exporter

CHANGELOG.md

@@ -10,19 +10,22 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 - `table` export has feature to customize n/a-value, which by default is the empty string
 - Add `conllu` as export format
 - import of `conllu` now supports enhanced dependencies
+- Adds `saltxml` export format
 
 ### Changed
 
 - `exmaralda` import now ranks order of tlis higher than sorting by time value (more compatible with modern EXMARaLDA files)
+- `xlsx` importer will connect spans to their corresponding segmentation node
+  with coverage edges instead of connecting them with the base tokens generated
+  for the timeline items. Thus, the configured connection between spans and base
+  text is not lost.
 
 ### Fixed
 
 - `exmaralda` import keeps events with missing time values
 
 ## [0.15.0] - 2024-08-14
 
-## [0.15.0] - 2024-08-14
-
 ### Added
 
 - New command line argument `--in-memory` that has the same meaning as setting

Cargo.toml

@@ -14,15 +14,16 @@ version = "0.15.0"
 [dependencies]
 ansi_term = "0.12"
 anyhow = "1.0"
+bimap = "0.6.3"
 clap = {version = "4.0", features = ["derive", "env"]}
 console = "0.15"
 csv = "1.1"
 documented = "0.3.0"
 encoding_rs = "0.8"
 encoding_rs_io = "0.1.7"
 glob = "0.3"
-graphannis = "3.3.3"
-graphannis-core = "3.3.3"
+graphannis = "3.4"
+graphannis-core = "3.4"
 graphviz-rust = "0.9.0"
 indicatif = "0.17"
 itertools = "0.12"
@@ -51,7 +52,7 @@ text-splitter = "0.6.3"
 thiserror = "1.0"
 toml = "0.8.0"
 tracing-subscriber = {version = "0.3", features = ["env-filter"]}
-umya-spreadsheet = "~1.1.1"
+umya-spreadsheet = "2.0.1"
 url = "2.5.2"
 xml-rs = "0.8"
 zip = "0.6.6"

src/error.rs

@@ -15,13 +15,13 @@ pub type StandardErrorResult<T> = std::result::Result<T, Box<dyn std::error::Err
 pub enum AnnattoError {
     #[error("Conversion failed with errors: {}", errors.iter().map(|e| e.to_string()).join("\n"))]
     ConversionFailed { errors: Vec<AnnattoError> },
-    #[error("Error during exporting corpus from {path} with {exporter:?}: {reason:?}")]
+    #[error("Error during exporting corpus to {path} with {exporter:?}: {reason:?}")]
     Export {
         reason: String,
         exporter: String,
         path: PathBuf,
     },
-    #[error("Error during importing corpus to {path} with {importer:?}: {reason:?}")]
+    #[error("Error during importing corpus from {path} with {importer:?}: {reason:?}")]
     Import {
         reason: String,
         importer: String,
@@ -75,11 +75,13 @@ pub enum AnnattoError {
     #[error("Could not parse TOML workflow file: {error}")]
     TOMLError { error: String },
     #[error("Could not read XSLS file: {0}")]
-    XlsxRead(#[from] umya_spreadsheet::reader::xlsx::XlsxError),
+    XlsxRead(#[from] umya_spreadsheet::XlsxError),
     #[error("Error waiting for finished conversion thread")]
     JoinHandle,
     #[error("Glob pattern caused an error: {0}")]
     GlobError(String),
+    #[error(transparent)]
+    Anyhow(#[from] anyhow::Error),
 }
 
 impl<T> From<std::sync::PoisonError<T>> for AnnattoError {

src/exporter/mod.rs

@@ -3,6 +3,7 @@
 pub mod conllu;
 pub mod exmaralda;
 pub mod graphml;
+pub mod saltxml;
 pub mod sequence;
 pub(crate) mod table;
 pub mod textgrid;