Skip to content

utils

Utility functions for parsing.

Small helper functions used across parser modules.

Functions

calculate_input_size 

calculate_input_size(file_paths: list[Path]) -> int | None

Calculate total size of input files.

Parameters:

Name Type Description Default
file_paths list[Path]

List of input file paths.

 required

Returns:

Type Description
int | None

Total size in bytes, or None if any file doesn't exist.
Source code in snakesee/parser/utils.py 
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
def calculate_input_size(file_paths: list[Path]) -> int | None:
    """
    Calculate total size of input files.

    Args:
        file_paths: List of input file paths.

    Returns:
        Total size in bytes, or None if any file doesn't exist.
    """
    total_size = 0
    for path in file_paths:
        try:
            total_size += path.stat().st_size
        except OSError:
            return None  # File doesn't exist or can't be accessed
    return total_size if file_paths else None

estimate_input_size_from_output 

estimate_input_size_from_output(output_path: Path, workflow_dir: Path) -> int | None

Try to estimate input size by looking for related input files.

This is a heuristic that works for common bioinformatics patterns where output files are derived from inputs with predictable naming conventions.

Examples:

  • sample.sorted.bam -> sample.bam
  • sample.fastq.gz -> looks for sample.fq.gz, sample.fastq.gz
  • sample.vcf.gz -> sample.bam

Parameters:

Name Type Description Default
output_path Path

Path to the output file.

 required
workflow_dir Path

Workflow root directory.

 required

Returns:

Type Description
int | None

Estimated input size in bytes, or None if not determinable.
Source code in snakesee/parser/utils.py 
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
def estimate_input_size_from_output(
    output_path: Path,
    workflow_dir: Path,
) -> int | None:
    """
    Try to estimate input size by looking for related input files.

    This is a heuristic that works for common bioinformatics patterns where
    output files are derived from inputs with predictable naming conventions.

    Examples:
        - sample.sorted.bam -> sample.bam
        - sample.fastq.gz -> looks for sample.fq.gz, sample.fastq.gz
        - sample.vcf.gz -> sample.bam

    Args:
        output_path: Path to the output file.
        workflow_dir: Workflow root directory.

    Returns:
        Estimated input size in bytes, or None if not determinable.
    """
    # Common input file patterns relative to output
    suffixes_to_strip = [
        ".sorted.bam",
        ".sorted",
        ".trimmed",
        ".filtered",
        ".dedup",
        ".aligned",
    ]

    name = output_path.name

    # Try stripping common suffixes to find input
    for suffix in suffixes_to_strip:
        if name.endswith(suffix):
            input_name = name[: -len(suffix)]
            # Try common extensions
            for ext in [".bam", ".fastq.gz", ".fq.gz", ".fa.gz", ".fasta.gz"]:
                candidate = workflow_dir / (input_name + ext)
                if candidate.exists():
                    try:
                        return candidate.stat().st_size
                    except OSError:
                        continue

    # No input found
    return None