mzident 0.2.1

Handle all kinds of PSM files.
Documentation
1
2
3
4
5
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
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
use std::{borrow::Cow, ops::Range, str::FromStr};

use context_error::*;
use mzcore::csv::CsvLine;

/// The way to set up a format family.
///
/// It starts with defining the name, complexity, peptidoform availability, all versions (parsing
/// is tried in this order), which separator is used for CSV files (character separated values),
/// and if needed the header for CSV files.
///
/// After that the columns are defined, first the required columns (present in all format versions)
/// followed by the optional columns (missing/optional in at least one version). For each column,
/// the name, type, and the lambda function to parse the text are given. Note that optional column
/// types are automatically wrapped in an `Option` so no additional `Option` should be specified.
///
/// Lastly, a postprocessing function can be specified.
///
/// Please check the other file formats for how the precisely use the syntax.
///
/// # Notes
/// * Do not forget to implement `PSMMetaData` for the `<$format>PSM` type, this will set up the
///   logic for an automatic `From<format> for PSMData` implementation.
/// * Do not forget to create a `<$format>Version` enum which contains all supported version of the
///   format, which additionally should implement `PSMFileFormatVersion`.
/// * For each version a public constant should be generated that contains an instantiation of the
///   `<$format>Format` type, these are also the ones that need to be listed in the versions list.
macro_rules! format_family {
     ($(#[doc = $ddoc:expr])*
     $format:ident,
     $complexity:ident, $peptidoform_availability:ident, $versions:expr, $separator:expr, $header:expr;
     required { $($(#[doc = $rdoc:expr])? $rname:ident: $rtyp:ty, $rf:expr;)* }
     optional { $($(#[doc = $odoc:expr])? $(#[cfg(feature = $ocfg:literal)])? $oname:ident: $otyp:ty, $of:expr;)*}
     $($post_process:item)?
     $(protein {
            $accession_name:ident => $accessionf:expr;
            required { $($(#[doc = $prdoc:expr])? $prname:ident: $prtyp:ty, $prf:expr;)* }
            optional { $($(#[doc = $podoc:expr])? $(#[cfg(feature = $pocfg:literal)])? $poname:ident: $potyp:ty, $pof:expr;)*}
    })?
    ) => {paste::paste!{
        #[allow(unused_imports)] // Needed sometimes, but not all invocations of the macro
        use context_error::*;

        use super::super::common_parser::HasLocation;

        #[doc = "The type to contain the format description for " $format " files."]
        #[non_exhaustive]
        #[derive(Clone, Debug, Default, Deserialize, Eq, Hash, Ord, PartialEq, PartialOrd, Serialize)]
        pub struct [<$format Format>] {
            $($rname: &'static str,)*
            $($(#[cfg(feature = $ocfg)])?  $oname: crate::common_parser::OptionalColumn,)*
            $(
                $accession_name: &'static str,
                $($prname: &'static str,)*
                $($(#[cfg(feature = $pocfg)])?  $poname: crate::common_parser::OptionalColumn,)*
            )?
            /// The version of this format
            pub version: [<$format Version>]
        }

        #[doc = "The data for individual entries in " $format " files."]
        $(#[doc = $ddoc])*
        #[non_exhaustive]
        #[derive(Clone, Debug, Default, Deserialize, PartialEq, Serialize)]
        #[allow(missing_docs)]
        pub struct [<$format PSM>] {
            $($(#[doc = $rdoc])? pub $rname: $rtyp,)*
            $($(#[doc = $odoc])? $(#[cfg(feature = $ocfg)])?  pub $oname: Option<$otyp>,)*
            /// The version used to read in the data
            pub version: [<$format Version>],
            /// The stored columns if kept
            columns: Option<Vec<(std::sync::Arc<String>, String)>>,
            $(
            pub $accession_name: std::sync::Arc<<[<$format PSM>] as PSMMetaData>::Protein>
            )?
        }

        $(
            #[doc = "The data for proteins in " $format " files."]
            #[non_exhaustive]
            #[derive(Clone, Debug, Default, Deserialize, PartialEq, Serialize)]
            #[allow(missing_docs)]
            pub struct [<$format Protein>] {
                pub $accession_name: String,
                $($(#[doc = $prdoc])? pub $prname: $prtyp,)*
                $($(#[doc = $podoc])? $(#[cfg(feature = $pocfg)])?  pub $poname: Option<$potyp>,)*
            }

            impl mzcore::space::Space for [<$format Protein>] {
                fn space(&self) -> mzcore::space::UsedSpace {
                    ( mzcore::space::UsedSpace::default()
                    $(+ self.$prname.space())*
                    $(+ {$(#[cfg(feature = $pocfg)])? self.$poname.space()})*)
                    .set_total::<Self>()
                }
            }

            impl From<[<$format Protein>]> for crate::ProteinData {
            fn from(value: [<$format Protein>]) -> Self {
                Self::$format(value)
            }
        }
        )?

        impl PSMSource for [<$format PSM>] {
            type Source = CsvLine;
            type Format = [<$format Format>];
            type Complexity = $complexity;
            type PeptidoformAvailability = $peptidoform_availability;
            type Version = [<$format Version>];
            const VERSIONS: &[&Self::Format] = &$versions;

            fn parse(source: &Self::Source, ontologies: &mzcore::ontology::Ontologies, keep_all_columns: bool, proteins: &mut std::collections::HashMap<String, std::sync::Arc<<[<$format PSM>] as PSMMetaData>::Protein>>) -> Result<(Self, &'static Self::Format), BoxedError<'static, BasicKind>> {
                let mut errors = Vec::new();
                for format in $versions {
                    match Self::parse_specific(source, format, ontologies, keep_all_columns, proteins) {
                        Ok(peptide) => return Ok((peptide, format)),
                        Err(err) => errors.push(err.version(format.version.to_string())),
                    }
                }
                Err(BoxedError::new(BasicKind::Error,
                    format!("Invalid {} line", stringify!($format)),
                    "The correct format could not be determined automatically",
                    source.full_context().to_owned(),
                ).add_underlying_errors(errors))
            }

            fn parse_file(
                path: impl AsRef<std::path::Path>,
                ontologies: &mzcore::ontology::Ontologies,
                keep_all_columns: bool,
                version: Option<Self::Version>,
            ) -> Result<BoxedIdentifiedPeptideIter<'_, Self>, BoxedError<'static, BasicKind>> {
                let format = version.map(|v| v.format());
                parse_csv(path, $separator, $header).and_then(|lines| {
                    let mut i = Self::parse_many::<Box<dyn Iterator<Item = Result<Self::Source, BoxedError<'_, BasicKind>>>>>(
                        Box::new(lines), ontologies, keep_all_columns, format);
                    if let Some(Err(e)) = i.peek() {
                        Err(e.clone())
                    } else {
                        Ok(i)
                    }
                })
            }

            fn parse_reader<'a>(
                reader: impl std::io::Read + 'a,
                ontologies: &'a mzcore::ontology::Ontologies,
                keep_all_columns: bool,
                version: Option<Self::Version>,
            ) -> Result<BoxedIdentifiedPeptideIter<'a, Self>, BoxedError<'static, BasicKind>> {
                let format = version.map(|v| v.format());
                mzcore::csv::parse_csv_raw(reader, $separator, $header, None).and_then(move |lines| {
                    let mut i = Self::parse_many::<Box<dyn Iterator<Item = Result<Self::Source, BoxedError<'_, BasicKind>>>>>(
                        Box::new(lines), ontologies, keep_all_columns, format);
                    if let Some(Err(e)) = i.peek() {
                        Err(e.clone())
                    } else {
                        Ok(i)
                    }
                })
            }

            #[allow(clippy::redundant_closure_call, unused_variables)] // Macro magic
            fn parse_specific(source: &Self::Source, format: &[<$format Format>], ontologies: &mzcore::ontology::Ontologies, keep_all_columns: bool, proteins: &mut std::collections::HashMap<String, std::sync::Arc<<[<$format PSM>] as PSMMetaData>::Protein>>) -> Result<Self, BoxedError<'static, BasicKind>> {
                #[allow(unused_imports)]
                use crate::helper_functions::InvertResult;

                /// Shadowing `Result::Ok` to inject the correct error type which otherwise leads
                /// to the compiler complaining about its absence when a field cannot fail.
                #[allow(non_snake_case, dead_code, clippy::missing_errors_doc)]
                const fn Ok<T>(value: T) -> Result<T, BoxedError<'static, BasicKind>> {
                    Result::Ok(value)
                }

                $(
                    let key = $accessionf(source.column(format.$accession_name).map_err(BoxedError::to_owned)?, ontologies)?;

                    let protein = if let Some(p) = proteins.get(&key) {
                        p.clone()
                    } else {
                        // Get around parser limitations by creating a type synonym.
                        type TempProtein = <[<$format PSM>] as PSMMetaData>::Protein;
                        let parsed = std::sync::Arc::new(TempProtein {
                            $accession_name: key.clone(),
                            $($prname: $prf(source.column(format.$prname).map_err(BoxedError::to_owned)?, ontologies)?,)*
                            $($(#[cfg(feature = $pocfg)])?  $poname: format.$poname.open_column(source).and_then(|l: Option<Location>| l.map(|value: Location| $pof(value, ontologies)).invert()).map_err(BoxedError::to_owned)?,)*
                        });
                        proteins.insert(key, parsed.clone());
                        parsed
                    };
                )?

                let parsed = Self {
                    $($rname: $rf(source.column(format.$rname).map_err(BoxedError::to_owned)?, ontologies)?,)*
                    $($(#[cfg(feature = $ocfg)])?  $oname: format.$oname.open_column(source).and_then(|l: Option<Location>| l.map(|value: Location| $of(value, ontologies)).invert()).map_err(BoxedError::to_owned)?,)*
                    version: format.version.clone(),
                    columns: keep_all_columns.then(|| source.values().map(|(h, v)| (h, v.to_string())).collect()),
                    $($accession_name: protein,)?
                };
                Self::post_process(source, parsed, ontologies)
            }
            $($post_process)?
        }

        impl [<$format PSM>] {
            /// Get all original columns from the CSV file, only available if the file was opened with the option `keep_all_columns` turned on.
            pub fn full_csv_line(&self) -> Option<&[(std::sync::Arc<String>, String)]> {
                self.columns.as_deref()
            }
        }

        impl From<[<$format PSM>]> for PSM<$complexity, $peptidoform_availability> {
            fn from(value: [<$format PSM>]) -> Self {
                Self {
                    score: value.confidence(),
                    local_confidence: value.local_confidence().map(|v| v.to_vec()),
                    data: PSMData::$format(value),
                    complexity_marker: PhantomData,
                    peptidoform_availability_marker: PhantomData,
                }
            }
        }

        impl mzcore::space::Space for [<$format PSM>] {
            fn space(&self) -> mzcore::space::UsedSpace {
                ( mzcore::space::UsedSpace::default()
                $(+ self.$rname.space())*
                $(+ {$(#[cfg(feature = $ocfg)])? self.$oname.space()})*)
                .set_total::<Self>()
            }
        }
    }};
}

/// The possible options for an optional column
#[derive(
    Copy,
    Clone,
    PartialEq,
    Eq,
    PartialOrd,
    Ord,
    Hash,
    Debug,
    Default,
    serde::Serialize,
    serde::Deserialize,
)]
pub(super) enum OptionalColumn {
    /// This column is not available in this version
    #[default]
    NotAvailable,
    /// This column is optional in this version
    Optional(&'static str),
    /// This column is required in this version (but as it is an `OptionalColumn` not in some other
    /// version)
    Required(&'static str),
}

impl OptionalColumn {
    /// Open the column
    /// # Errors
    /// while creating the correct error messages for missing columns
    pub(super) fn open_column(
        self,
        source: &CsvLine,
    ) -> Result<Option<Location<'_>>, BoxedError<'static, BasicKind>> {
        match self {
            Self::NotAvailable => Ok(None),
            Self::Optional(s) => Ok(source.column(s).ok()),
            Self::Required(s) => source.column(s).map(Some),
        }
    }
}

pub(super) trait HasLocation {
    /// Get the specified column.
    /// # Errors
    /// If the column does not exist.
    fn column<'a>(&'a self, name: &'a str) -> Result<Location<'a>, BoxedError<'static, BasicKind>>;
}

impl HasLocation for CsvLine {
    /// Get the specified column
    /// # Errors
    /// If the given column does not exist
    fn column<'a>(&'a self, name: &'a str) -> Result<Location<'a>, BoxedError<'static, BasicKind>> {
        self.index_column(name)
            .map(|(_v, c)| Location {
                line: self,
                range: c.clone(),
                column: Some(name),
            })
            .map_err(BoxedError::to_owned)
    }
}

/// The base location type to keep track of the location of to be parsed pieces in the monadic
/// parser combinators below
#[derive(Clone)]
pub(super) struct Location<'a> {
    pub(super) line: &'a CsvLine,
    pub(super) range: Range<usize>,
    pub(super) column: Option<&'a str>,
}

impl Location<'_> {
    pub(super) fn len(&self) -> usize {
        self.range.len()
    }

    pub(super) fn is_empty(&self) -> bool {
        self.range.is_empty()
    }

    pub(super) fn array(self, sep: char) -> std::vec::IntoIter<Self> {
        let mut offset = 0;
        let mut output = Vec::new();
        for part in self.as_str().split(sep) {
            output.push(Location {
                line: self.line,
                range: self.range.start + offset..self.range.start + offset + part.len(),
                column: self.column,
            });
            offset += part.len() + 1;
        }
        output.into_iter()
    }

    pub(super) fn or_empty(self) -> Option<Self> {
        let text = self.as_str();
        if text.is_empty() || text == "-" {
            None
        } else {
            Some(self)
        }
    }

    pub(super) fn ignore(self, pattern: &str) -> Option<Self> {
        let text = self.as_str();
        if text == pattern { None } else { Some(self) }
    }

    pub(super) fn skip(self, bytes: usize) -> Self {
        Self {
            line: self.line,
            range: self.range.start.saturating_add(bytes).min(self.range.end)..self.range.end,
            column: self.column,
        }
    }

    pub(super) fn trim_end_matches(mut self, pattern: &str) -> Self {
        let trimmed = self.as_str().trim_end_matches(pattern);
        let dif = self.range.len() - trimmed.len();
        self.range = self.range.start..self.range.end - dif;
        self
    }

    pub(super) fn trim_start_matches(mut self, pattern: &str) -> Self {
        let trimmed = self.as_str().trim_start_matches(pattern);
        let dif = self.range.len() - trimmed.len();
        self.range = self.range.start + dif..self.range.end;
        self
    }

    pub(super) fn get_string(self) -> String {
        self.as_str().to_string()
    }

    pub(super) fn get_boxed_str(self) -> Box<str> {
        self.as_str().into()
    }

    pub(super) fn as_str(&self) -> &str {
        &self.line.line()[self.range.clone()]
    }

    pub(super) fn full_line(&self) -> &str {
        self.line.line()
    }
}

impl<'a> Location<'a> {
    /// # Errors
    /// If the parse method fails. See [`FromStr::parse`].
    pub(super) fn parse<T: FromStr>(
        self,
        base_error: (&'static str, &'static str),
    ) -> Result<T, BoxedError<'static, BasicKind>> {
        self.as_str().trim().parse().map_err(|_| {
            BoxedError::new(
                BasicKind::Error,
                base_error.0,
                base_error.1,
                self.line
                    .range_context(self.range, self.column.map(Cow::Borrowed))
                    .to_owned(),
            )
        })
    }

    /// # Errors
    /// If the provided parse method fails.
    pub(super) fn parse_with<T>(
        self,
        f: impl Fn(Self) -> Result<T, BoxedError<'static, BasicKind>>,
    ) -> Result<T, BoxedError<'static, BasicKind>> {
        f(self)
    }

    pub(super) fn base_context(&'a self) -> Context<'a> {
        let base = Context::default()
            .line_index(self.line.line_index as u32)
            .lines(0, self.full_line());
        if let Some(source) = &self.line.file {
            base.source(source.as_ref().as_ref())
        } else {
            base
        }
    }

    pub(super) fn context(&'a self) -> Context<'a> {
        let base = self.base_context();
        if let Some(comment) = self.column {
            base.add_highlight((0, self.range.clone(), comment))
        } else {
            base.add_highlight((0, self.range.clone()))
        }
    }

    pub(super) fn trim(&self) -> Self {
        let str = self.as_str();
        let length = str.len();
        let trimmed_start = length - str.trim_start().len();
        let trimmed_end = length - str.trim_end().len();

        Self {
            line: self.line,
            range: if self.range.start + trimmed_end > self.range.end - trimmed_end {
                self.range.start..self.range.start
            } else {
                self.range.start + trimmed_start..self.range.end - trimmed_end
            },
            column: self.column,
        }
    }

    pub(super) fn split_once(self, p: char) -> Option<(Self, Self)> {
        self.as_str().split_once(p).map(|(start, end)| {
            (
                Self {
                    line: self.line,
                    range: self.range.start..self.range.start + start.len(),
                    column: self.column,
                },
                Self {
                    line: self.line,
                    range: self.range.end - end.len()..self.range.end,
                    column: self.column,
                },
            )
        })
    }

    /// Split twice on the character, split on the first and last occurrence of the given character.
    /// So any additional occurrences of the characters are in the middle segment.
    pub(super) fn split_twice(self, p: char) -> Option<(Self, Self, Self)> {
        let (start, after) = self.as_str().split_once(p)?;
        let (middle, end) = after.rsplit_once(p)?;
        let start_middle = self.range.start + start.len() + p.len_utf8();
        Some((
            Self {
                line: self.line,
                range: self.range.start..self.range.start + start.len(),
                column: self.column,
            },
            Self {
                line: self.line,
                range: start_middle..start_middle + middle.len(),
                column: self.column,
            },
            Self {
                line: self.line,
                range: self.range.end - end.len()..self.range.end,
                column: self.column,
            },
        ))
    }
}

pub(super) trait OptionalLocation<'a> {
    /// # Errors
    /// If the parse method fails. See [`FromStr::parse`].
    fn parse<T: FromStr>(
        self,
        base_error: (&'static str, &'static str),
    ) -> Result<Option<T>, BoxedError<'static, BasicKind>>;
    /// # Errors
    /// If the provided parse method fails.
    fn parse_with<T>(
        self,
        f: impl Fn(Location<'a>) -> Result<T, BoxedError<'static, BasicKind>>,
    ) -> Result<Option<T>, BoxedError<'static, BasicKind>>;
    fn get_string(self) -> Option<String>;
    type ArrayIter: Iterator<Item = Location<'a>>;
    fn array(self, sep: char) -> Self::ArrayIter;
    fn optional_array(self, sep: char) -> Option<Self::ArrayIter>;
    fn ignore(self, pattern: &str) -> Option<Location<'a>>;
}

impl<'a> OptionalLocation<'a> for Option<Location<'a>> {
    type ArrayIter = std::vec::IntoIter<Location<'a>>;

    fn parse<T: FromStr>(
        self,
        base_error: (&'static str, &'static str),
    ) -> Result<Option<T>, BoxedError<'static, BasicKind>> {
        self.map(|l| l.parse::<T>(base_error)).transpose()
    }

    fn parse_with<T>(
        self,
        f: impl Fn(Location<'a>) -> Result<T, BoxedError<'static, BasicKind>>,
    ) -> Result<Option<T>, BoxedError<'static, BasicKind>> {
        self.map(f).transpose()
    }

    fn get_string(self) -> Option<String> {
        self.map(Location::get_string)
    }

    fn array(self, sep: char) -> Self::ArrayIter {
        self.map(|l| l.array(sep)).unwrap_or_default()
    }

    fn optional_array(self, sep: char) -> Option<Self::ArrayIter> {
        self.map(|l| l.array(sep))
    }

    fn ignore(self, pattern: &str) -> Self {
        self.and_then(|s| s.ignore(pattern))
    }
}