Skip to content

Save hash and path grid informations when generating FK Tables #247

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
scarlehoff merged 6 commits into from
Jun 1, 2026
Merged

Save hash and path grid informations when generating FK Tables #247

Show file tree
Hide file tree
Changes from 3 commits
Commits
Show all changes
6 commits
Select commit Hold shift + click to select a range
3e9a620
add hash and parth information when generating FK Tables
Apr 28, 2026
e12865f
resolved conflicts
May 26, 2026
0a184f6
made info in the metadata more readable; removed absolute path from m…
May 26, 2026
6f6f402
simplified metadata
May 27, 2026
bbf62d2
Addressing metadata of merged FK Tables
May 28, 2026
aef36cf
re-run pre-commit
Jun 1, 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
1 change: 1 addition & 0 deletions src/pineko/cli/convolve.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -108,6 +108,7 @@ def subcommand(
assumptions=assumptions,
comparison_pdfs=pdfs,
min_as=min_as,
grid_path=pathlib.Path(grid_path),
)

if len(operators) > 1:
Expand Down
46 changes: 43 additions & 3 deletions src/pineko/evolve.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,6 +1,7 @@
"""Tools related to evolution/eko."""

import copy
import hashlib
import json
import logging
import os
Expand Down Expand Up @@ -67,7 +68,7 @@ def construct_atlas(tcard):
return atlas


def construct_empty_fktable(grid, theory_meta, fktable_path):
def construct_empty_fktable(grid, theory_meta, fktable_path, grid_path=None):
"""Construct and write a structurally valid but numerically empty FK table.

"Empty" means the FK table carries a single trivial order ``(0,0,0,0,0)``
Expand Down Expand Up @@ -113,6 +114,21 @@ def construct_empty_fktable(grid, theory_meta, fktable_path):
fktable = pineappl.fk_table.FkTable(empty_grid)
fktable.set_metadata("pineko_version", version.__version__)
fktable.set_metadata("theory_card", json.dumps(theory_meta))
if grid_path is not None:
grid_path_obj = pathlib.Path(grid_path).resolve()
grid_hash = hashlib.md5(grid_path_obj.read_bytes()).hexdigest()
grid_path_parts = grid_path_obj.parts
if "pineko" in grid_path_parts:
pineko_idx = grid_path_parts.index("pineko")
display_path = str(pathlib.Path("/", *grid_path_parts[pineko_idx + 1 :]))
elif "data" in grid_path_parts:
data_idx = grid_path_parts.index("data")
display_path = str(pathlib.Path("/", *grid_path_parts[data_idx:]))
else:
display_path = grid_path_obj.name
fktable.set_metadata("grid_hash", grid_hash)
fktable.set_metadata("grid_theory", grid_path_obj.parent.name)
fktable.set_metadata("grid_path", display_path)

@felixhekhorn felixhekhorn May 26, 2026

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

  1. This is far too much code duplication - this needs to be encapsulated
  2. do we really need grid_path? this looks fairly complicated ...

@scarlehoff scarlehoff May 26, 2026

Copy link
Copy Markdown
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Yes, the grids path part is a bit more complicated than needed, data/grids are not important.

Once you have the grid path, the "path of the grid itself" is grid_path.name and the theory folder grid_path.parent.name. You don't need anything else.

@kamillaurent kamillaurent May 27, 2026

Copy link
Copy Markdown
Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

I tried to simplify the metadata, using a function and calling it when the FK table is constructed (so there is no code duplication):

def set_fktable_metadata(fktable, theory_meta, grid_path=None):
    """Store the common FK metadata and, if available, grid provenance."""
    fktable.set_metadata("pineko_version", version.__version__)
    fktable.set_metadata("theory_card", json.dumps(theory_meta))
    if grid_path is None:
        return

    grid_path_obj = pathlib.Path(grid_path).resolve()
    grid_hash = hashlib.md5(grid_path_obj.read_bytes()).hexdigest()
    fktable.set_metadata("grid_hash", grid_hash)
    fktable.set_metadata("grid_theory", grid_path_obj.parent.name)
    fktable.set_metadata("grid_name", grid_path_obj.name)

For consistency I moved into the function also pineko_version and theory_card. I removed the path since the relevant information is the name of the folder, which is also the theory ID.

fktable.write_lz4(str(fktable_path))
return fktable

Expand Down Expand Up @@ -353,6 +369,7 @@ def evolve_grid(
assumptions="Nf6Ind",
comparison_pdfs: Optional[list[str]] = None,
min_as=None,
grid_path: Optional[os.PathLike] = None,
):
"""Convolute grid with EKO from file paths.

Expand Down Expand Up @@ -382,6 +399,8 @@ def evolve_grid(
if given, a comparison table (with / without evolution) will be printed
min_as: None or int
minimum power of strong coupling
grid_path : str or os.PathLike or None
path to the grid file, used to store grid hash metadata

Returns
-------
Expand All @@ -399,7 +418,9 @@ def evolve_grid(
# A grid with no orders is a valid input for some workflows. In that case we
# cannot build evolution kinematics, so we directly emit an empty FK table.
if len(grid.orders()) == 0:
fktable = construct_empty_fktable(grid, theory_meta, fktable_path)
fktable = construct_empty_fktable(
grid, theory_meta, fktable_path, grid_path=grid_path
)
return grid, fktable, None

order_mask = pineappl.boc.Order.create_mask(grid.orders(), max_as, max_al, True)
Expand All @@ -423,7 +444,9 @@ def evolve_grid(
# `XGrid` requires at least 2 points, otherwise it panics. In this case, we
# simply return an empty FK table instead.
if (len(x_grid) < 2) or (len(muf2_grid) == 0) or (len(mur2_grid) == 0):
fktable = construct_empty_fktable(grid, theory_meta, fktable_path)
fktable = construct_empty_fktable(
grid, theory_meta, fktable_path, grid_path=grid_path
)
return grid, fktable, None

xif = 1.0 if operators[0].operator_card.configs.scvar_method is not None else xif
Expand Down Expand Up @@ -510,6 +533,23 @@ def prepare(operator, convolution_types):
fktable.set_metadata("pineko_version", version.__version__)
fktable.set_metadata("theory_card", json.dumps(theory_meta))

# Store grid hash, theory folder, and repo-style grid path information
if grid_path is not None:
grid_path_obj = pathlib.Path(grid_path).resolve()
grid_hash = hashlib.md5(grid_path_obj.read_bytes()).hexdigest()
grid_path_parts = grid_path_obj.parts
if "pineko" in grid_path_parts:
pineko_idx = grid_path_parts.index("pineko")
display_path = str(pathlib.Path("/", *grid_path_parts[pineko_idx + 1 :]))
elif "data" in grid_path_parts:
data_idx = grid_path_parts.index("data")
display_path = str(pathlib.Path("/", *grid_path_parts[data_idx:]))
else:
display_path = grid_path_obj.name
fktable.set_metadata("grid_hash", grid_hash)
fktable.set_metadata("grid_theory", grid_path_obj.parent.name)
fktable.set_metadata("grid_path", display_path)

# compare before/after
comparison = None
if comparison_pdfs is not None:
Expand Down
1 change: 1 addition & 0 deletions src/pineko/theory.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -562,6 +562,7 @@ def fk(self, name, grid_path, tcard, pdfs):
theory_meta=tcard,
assumptions=assumptions,
comparison_pdfs=pdfs,
grid_path=grid_path,
)

if n_ekos > 1:
Expand Down
Loading