Feature: rich compiler prompts when coding in modern editors

.github/workflows/codespell.yml

@@ -0,0 +1,44 @@
+# Codespell configuration is within pyproject.toml
+---
+name: Codespell
+
+on: [push]
+#on:
+#  push:
+#    branches: [main]
+#  pull_request:
+#    branches: [main]
+
+permissions:
+  contents: read
+
+jobs:
+  codespell:
+    name: Check for spelling errors
+    runs-on: ubuntu-latest
+
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v4
+      - name: Codespell
+        uses: codespell-project/actions-codespell@v2
+        with:
+          ignore_words_list: Crate,crate,fo,tre
+
+  formatting:
+    permissions:
+      contents: read # for actions/checkout to fetch code
+      pull-requests: write # for marocchino/sticky-pull-request-comment to create or update PR comment
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+
+      - uses: mamba-org/setup-micromamba@v1
+        with:
+          environment-name: black
+          create-args: -c bioconda -c conda-forge black
+          cache-environment: false
+
+      - name: Check formatting
+        shell: bash -el {0}
+        run: black --check --diff .

.github/workflows/pytest.yml

@@ -0,0 +1,32 @@
+name: pytest
+
+on: [push]
+
+jobs:
+  testing:
+    runs-on: ubuntu-latest
+    strategy:
+      fail-fast: false
+      matrix:
+        python-version: ["3.9", "3.11", "3.13"]
+
+    steps:
+      - uses: actions/checkout@v4
+      - name: Set up Python ${{ matrix.python-version }}
+        uses: actions/setup-python@v3
+        with:
+          python-version: ${{ matrix.python-version }}
+      - name: Install lib from source
+        shell: bash -el {0}
+        run: |
+          python -m pip install --upgrade pip pytest pandas
+          python -m pip install .
+
+      - name: Test local
+        env:
+          CI: true
+          #PYTHONTRACEMALLOC: 10
+        shell: bash -el {0}
+        run: |
+          python -m pytest -v --show-capture=stderr \
+            tests.py

README.rst

@@ -27,15 +27,15 @@ Records can be accessed through this list or by id. ``GenomeDiff`` is iterable a
 ::
 
     >>> from genomediff import *
-    >>> document = GenomeDiff.read(open('MyDiff.gd', 'r', encoding='utf-8'))
+    >>> document = GenomeDiff.read("MyDiff.gd")
     >>> document.metadata
-    {'GENOME_DIFF': '1.0', 'AUTHOR': ''}
+    {'GENOME_DIFF': ['1.0'], 'AUTHOR': ['']}
     >>> document.mutations[0]
     Record('SNP', 1, [191], new_seq='A', seq_id='NC_000913', snp_type='intergenic',  position=12346)
     >>> document.mutations[0].parent_ids
     [191]
     >>> document[191]
     Record('RA', 191, None, tot_cov='46/42', new_base='A', insert_position=0, ref_base='G', seq_id='NC_000913', quality=252.9, position=12345)
-    >>> document.mutations[0].parents
+    >>> document.records.parents_of[0]
     [Record('RA', 191, None, tot_cov='46/42', new_base='A', insert_position=0, ref_base='G', seq_id='NC_000913', quality=252.9, position=12345)]
     >>> document.write(open('NewDiff.gd', 'w', encoding='utf-8'))

src/genomediff/__init__.py

@@ -1,73 +1,78 @@
-import itertools
-from genomediff.parser import GenomeDiffParser
-from genomediff.records import Metadata
+# -*- coding: utf-8 -*-
+from pathlib import Path
+from typing import TextIO
 
+from .parser import Metadata, MetadataContainer, load_json_ref_cov, parse
+from .records import RecordCollection
 
-class GenomeDiff(object):
 
-    def __init__(self):
-        self.metadata = {}
-        self.mutations = []
-        self.evidence = []
-        self.validation = []
-        self._index = {}
+class GenomeDiff:
+    def __init__(
+        self,
+        metadata: MetadataContainer,
+        records: RecordCollection,
+        comments: "dict[int, str]|None" = None,
+    ):
+        self._metadata = metadata
+        self._records = records
+        self._comments = comments if comments else {}
 
-    @classmethod
-    def read(cls, fsock):
-        gd = GenomeDiff()
+    @property
+    def metadata(self):
+        return self._metadata
+
+    @property
+    def records(self):
+        return self._records
 
-        for record in GenomeDiffParser(document=gd, fsock=fsock):
+    @classmethod
+    def read(cls, gdfile: "str|Path|TextIO"):
+        records = RecordCollection.new()
+        comments: dict[int, str] = {}
+        if hasattr(gdfile, "read"):
+            metadata = MetadataContainer(getattr(gdfile, "name", ""))
+            fsock: TextIO = gdfile  # type: ignore[assignment]
+        else:
+            metadata = MetadataContainer(gdfile)
+            fsock = open(gdfile, "r")
+        self = cls(metadata, records, comments)
+        for i, record in parse(fsock):
             if isinstance(record, Metadata):
-                gd.metadata[record.name] = record.value
+                metadata.set(record.name, record.value)
+            elif isinstance(record, str):
+                comments[i] = record
             else:
-                if len(record.type) == 3:
-                    gd.mutations.append(record)
-                if len(record.type) == 2:
-                    gd.evidence.append(record)
-                if len(record.type) == 4:
-                    gd.validation.append(record)
-                gd._index[record.id] = record
-        return gd
-
-    def __getitem__(self, item):
-        return self._index[item]
+                record.document = self
+                records.set(record)
+        if not hasattr(gdfile, "read"):
+            fsock.close()
+        return self
 
     def write(self, fsock):
-        #Print our own version line first and ignore any in the metadata
-        print("#=GENOME_DIFF\t1.0", file = fsock)
-        for k, v in self.metadata.items():
-          if k != "GENOME_DIFF":
-            print("#={}\t{}".format(k, v), file = fsock)
-        for record in itertools.chain(self.mutations, self.evidence, self.validation):
-          print(str(record), file = fsock)
+        print("#=GENOME_DIFF\t1.0", file=fsock)
+        for l in self.metadata.lines:
+            if l.name != "GENOME_DIFF":
+                print(l, file=fsock)
+        for record in self.records:
+            print(str(record), file=fsock)
 
-    def __len__(self):
-        return len(self.mutations) + len(self.evidence) + len(self.validation)
+    @property
+    def cov_summary(self):
+        if outdir := self.metadata.output:
+            return load_json_ref_cov(outdir)
+        raise AttributeError("No output directory found in metadata")
 
-    def __iter__(self):
-        return itertools.chain(self.mutations, self.evidence, self.validation)
+    @property
+    def mutations(self):
+        return list(self.records.mutation)
 
-    def __str__(self):
-        return '\n'.join(["MUTATIONS:",'\n'.join([str(x) for x in self.mutations]),
-                          "EVIDENCE:",'\n'.join([str(x) for x in self.evidence]),
-                          "VALIDATION:",'\n'.join(self.validation)])
+    @property
+    def evidence(self):
+        return list(self.records.evidence)
 
+    @property
+    def validation(self):
+        return list(self.records.validation)
 
-    def remove(self,*args, mut_type=None):
-        '''
-        Remove mutations that satisfy the given conditions. Implementation of
-        gdtools REMOVE for genomediff objects.
-
-        Input: a variable number of conditions, e.g. 'gene_name==rrlA','frequency>=0.9'.
-               If mut_type is specified, only that mutation type will be removed.
-        Output: self.mutations is updated, with mutations satifying the conditions
-                having been removed.
-        '''
-        updated_mutations = []
-        for rec in self.mutations:
-            if (mut_type is None or mut_type == rec.type) and rec.satisfies(*args):
-                continue
-            else:
-                updated_mutations.append(rec)
-
-        self.mutations = updated_mutations
+    def __getitem__(self, key):
+        return self.records[key]