Skip to content

Fix ADF15 parser and refine regex patterns #497

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
jacklovell merged 6 commits into from
May 28, 2026
Merged

Fix ADF15 parser and refine regex patterns #497

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
6 commits
Select commit Hold shift + click to select a range
234ec15
Fix ADF15 parser
munechika-koyo Mar 11, 2026
b2cdca5
Fix regressions for config regex pattern in _scrape_metadata_full
munechika-koyo Mar 11, 2026
6157a17
Move regex pattern definition out of for-loop
munechika-koyo Mar 21, 2026
04ddbd7
Refine regex pattern for configuration string in _scrape_metadata_full
munechika-koyo Mar 22, 2026
4510034
Add unit tests for ADF15 parser with mock data for hydrogen, carbon, …
munechika-koyo May 18, 2026
51e85bf
Refactor string literals to use double quotes in ADF15 parser and tests
munechika-koyo May 18, 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
165 changes: 85 additions & 80 deletions cherab/openadas/parse/adf15.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -17,27 +17,52 @@
# under the Licence.

import re

import numpy as np
from cherab.core.atomic import hydrogen, Element

from cherab.core.atomic import Element, hydrogen
from cherab.core.utility import RecursiveDict
from cherab.core.utility.conversion import Cm3ToM3, PerCm3ToPerM3

# Compiled regex patterns for ADF15 file parsing
_ADF_HEADER_MATCH = re.compile(r"^\s*(\d*) {4}/(.*)/?\s*$")
_PEC_INDEX_HEADER_MATCH_STANDARD = re.compile(r"^C\s*ISEL\s*(?:WAVELENGTH|WVLEN\(A\))\s*TRANSITION\s*TYPE", re.IGNORECASE)
_PEC_HYDROGEN_TRANSITION_MATCH = re.compile(r"^C\s*([0-9]*)\.\s*([0-9]*\.[0-9]*)\s*N=\s*([0-9]*) - N=\s*([0-9]*)\s*([A-Z]*)", re.IGNORECASE)
_PEC_FULL_TRANSITION_MATCH = re.compile(r"^[cC]\s*([0-9]*)\.?\s*([0-9]*\.[0-9]*)\s*([0-9]*)[\(\)\.0-9\s]*-\s*([0-9]*)[\(\)\.0-9\s]*([A-Z]*)", re.IGNORECASE)
_CONFIGURATION_HEADER_MATCH = re.compile(r"^C\s*(?:lv\s+)?Configuration\s*\(2S\+1\)L\(w-1/2\)\s*Energy\s*\(cm(?:\*\*|\^)-1\)\s*$", re.IGNORECASE)
_CONFIGURATION_STRING_MATCH = re.compile(
r"^[cC]\s*([0-9]+)\s*"
r"((?:[0-9][SPDFG][0-9](?:\s+[0-9][SPDFG][0-9])*)|(?:[0-9A-Z]+))\s*"
r"\(([0-9]*\.?[0-9]+)\)"
r"\s*([0-9]+)"
r"\(\s*([0-9]*\.?[0-9]+)\)",
re.IGNORECASE,
)
_WAVELENGTH_MATCH = re.compile(r"^\s*[0-9]*\.[0-9]* ?a?\s+[0-9]+\s+[0-9]+.*?/isel *= *[0-9]+$", re.IGNORECASE)
_BLOCK_ID_MATCH = re.compile(r"^\s*[0-9]*\.[0-9]* ?a?\s*([0-9]*)\s*([0-9]*).*/type *= *([a-zA-Z]*).*/isel *= * ([0-9]*)$", re.IGNORECASE)

_L_LOOKUP = {
0: 'S',
1: 'P',
2: 'D',
3: 'F',
4: 'G',
5: 'H',
6: 'I',
7: 'K',
8: 'L',
9: 'M',
10: 'N',
11: 'O',
12: 'Q',
13: 'R',
0: "S",
1: "P",
2: "D",
3: "F",
4: "G",
5: "H",
6: "I",
7: "K",
8: "L",
9: "M",
10: "N",
11: "O",
12: "Q",
13: "R",
14: "T",
15: "U",
16: "V",
17: "W",
18: "X",
19: "Y",
20: "Z",
}


Expand All @@ -52,26 +77,25 @@ def parse_adf15(element, charge, adf_file_path, header_format=None):
"""

if not isinstance(element, Element):
raise TypeError('The element must be an Element object.')
raise TypeError("The element must be an Element object.")

charge = int(charge)

with open(adf_file_path, "r") as file:

# for check header line
header = file.readline()
if not re.match(r'^\s*(\d*) {4}/(.*)/?\s*$', header):
raise ValueError('The specified path does not point to a valid ADF15 file.')
if not _ADF_HEADER_MATCH.match(header):
raise ValueError("The specified path does not point to a valid ADF15 file.")

# scrape transition information and wavelength
# use simple electron configuration structure for hydrogen-like ions
if header_format == 'hydrogen' or element == hydrogen:
if header_format == "hydrogen" or element == hydrogen:
config = _scrape_metadata_hydrogen(file, element, charge)
elif header_format == 'hydrogen-like':
elif header_format == "hydrogen-like":
config = _scrape_metadata_hydrogen_like(file, element, charge)
elif element.atomic_number - charge == 1:
config = _scrape_metadata_hydrogen_like(file, element, charge)
if not config and 'bnd#' in adf_file_path:
if not config and "bnd#" in adf_file_path:
# ADF15 files with the "bnd" suffix may have metadata in the "hydrogen" format
config = _scrape_metadata_hydrogen(file, element, charge)
else:
Expand All @@ -82,14 +106,14 @@ def parse_adf15(element, charge, adf_file_path, header_format=None):

# process rate data
rates = RecursiveDict()
for cls in ('excitation', 'recombination', 'thermalcx'):
for cls in ("excitation", "recombination", "thermalcx"):
for element, charge_states in config[cls].items():
for charge, transitions in charge_states.items():
for transition in transitions.keys():
block_num = config[cls][element][charge][transition]
rates[cls][element][charge][transition] = _extract_rate(file, block_num)

wavelengths = config['wavelength']
wavelengths = config["wavelength"]
return rates, wavelengths


Expand All @@ -104,29 +128,25 @@ def _scrape_metadata_hydrogen(file, element, charge):
file.seek(0)
lines = file.readlines()

pec_index_header_match = r'^C\s*ISEL\s*WAVELENGTH\s*TRANSITION\s*TYPE'
while not re.match(pec_index_header_match, lines[0], re.IGNORECASE):
while not _PEC_INDEX_HEADER_MATCH_STANDARD.match(lines[0]):
lines.pop(0)
index_lines = lines

for i in range(len(index_lines)):

pec_hydrogen_transition_match = r'^C\s*([0-9]*)\.\s*([0-9]*\.[0-9]*)\s*N=\s*([0-9]*) - N=\s*([0-9]*)\s*([A-Z]*)'
match = re.match(pec_hydrogen_transition_match, index_lines[i], re.IGNORECASE)
match = _PEC_HYDROGEN_TRANSITION_MATCH.match(index_lines[i])
if not match:
continue

block_num = int(match.groups()[0])
wavelength = float(match.groups()[1]) / 10 # convert Angstroms to nm
upper_level = int(match.groups()[2])
lower_level = int(match.groups()[3])
rate_type_adas = match.groups()[4]
if rate_type_adas == 'EXCIT':
rate_type = 'excitation'
elif rate_type_adas == 'RECOM':
rate_type = 'recombination'
elif rate_type_adas == 'CHEXC':
rate_type = 'thermalcx'
rate_type_adas = match.groups()[4].upper()
if rate_type_adas == "EXCIT":
rate_type = "excitation"
elif rate_type_adas == "RECOM":
rate_type = "recombination"
elif rate_type_adas == "CHEXC":
rate_type = "thermalcx"
else:
raise ValueError("Unrecognised rate type - {}".format(rate_type_adas))

Expand All @@ -147,29 +167,25 @@ def _scrape_metadata_hydrogen_like(file, element, charge):
file.seek(0)
lines = file.readlines()

pec_index_header_match = r'^C\s*ISEL\s*WAVELENGTH\s*TRANSITION\s*TYPE'
while not re.match(pec_index_header_match, lines[0], re.IGNORECASE):
while not _PEC_INDEX_HEADER_MATCH_STANDARD.match(lines[0]):
lines.pop(0)
index_lines = lines

for i in range(len(index_lines)):

pec_full_transition_match = r'^C\s*([0-9]*)\.\s*([0-9]*\.[0-9]*)\s*([0-9]*)[\(\)\.0-9\s]*-\s*([0-9]*)[\(\)\.0-9\s]*([A-Z]*)'
match = re.match(pec_full_transition_match, index_lines[i], re.IGNORECASE)
match = _PEC_FULL_TRANSITION_MATCH.match(index_lines[i])
if not match:
continue

block_num = int(match.groups()[0])
wavelength = float(match.groups()[1]) / 10 # convert Angstroms to nm
upper_level = int(match.groups()[2])
lower_level = int(match.groups()[3])
rate_type_adas = match.groups()[4]
if rate_type_adas == 'EXCIT':
rate_type = 'excitation'
elif rate_type_adas == 'RECOM':
rate_type = 'recombination'
elif rate_type_adas == 'CHEXC':
rate_type = 'thermalcx'
rate_type_adas = match.groups()[4].upper()
if rate_type_adas == "EXCIT":
rate_type = "excitation"
elif rate_type_adas == "RECOM":
rate_type = "recombination"
elif rate_type_adas == "CHEXC":
rate_type = "thermalcx"
else:
raise ValueError("Unrecognised rate type - {}".format(rate_type_adas))

Expand All @@ -193,19 +209,14 @@ def _scrape_metadata_full(file, element, charge):
configuration_lines = []
configuration_dict = {}

configuration_header_match = r'^C\s*Configuration\s*\(2S\+1\)L\(w-1/2\)\s*Energy \(cm\*\*-1\)$'
while not re.match(configuration_header_match, lines[0], re.IGNORECASE):
while not _CONFIGURATION_HEADER_MATCH.match(lines[0]):
lines.pop(0)
pec_index_header_match = r'^C\s*ISEL\s*WAVELENGTH\s*TRANSITION\s*TYPE'
while not re.match(pec_index_header_match, lines[0], re.IGNORECASE):
while not _PEC_INDEX_HEADER_MATCH_STANDARD.match(lines[0]):
configuration_lines.append(lines[0])
lines.pop(0)
index_lines = lines

for i in range(len(configuration_lines)):

configuration_string_match = r"^C\s*([0-9]*)\s*((?:[0-9][SPDFG][0-9]\s)*)\s*\(([0-9]*\.?[0-9]*)\)([0-9]*)\(\s*([0-9]*\.?[0-9]*)\)"
match = re.match(configuration_string_match, configuration_lines[i], re.IGNORECASE)
match = _CONFIGURATION_STRING_MATCH.match(configuration_lines[i])
if not match:
continue

Expand All @@ -215,13 +226,10 @@ def _scrape_metadata_full(file, element, charge):
total_orbital_quantum_number = _L_LOOKUP[int(match.groups()[3])] # L
total_angular_momentum_quantum_number = match.groups()[4] # J

configuration_dict[config_id] = (electron_configuration + " " + spin_multiplicity +
total_orbital_quantum_number + total_angular_momentum_quantum_number)
configuration_dict[config_id] = electron_configuration + " " + spin_multiplicity + total_orbital_quantum_number + total_angular_momentum_quantum_number

for i in range(len(index_lines)):

pec_full_transition_match = r'^C\s*([0-9]*)\.?\s*([0-9]*\.[0-9]*)\s*([0-9]*)[\(\)\.0-9\s]*-\s*([0-9]*)[\(\)\.0-9\s]*([A-Z]*)'
match = re.match(pec_full_transition_match, index_lines[i], re.IGNORECASE)
match = _PEC_FULL_TRANSITION_MATCH.match(index_lines[i])
if not match:
continue

Expand All @@ -231,13 +239,13 @@ def _scrape_metadata_full(file, element, charge):
upper_level = configuration_dict[upper_level_id]
lower_level_id = int(match.groups()[3])
lower_level = configuration_dict[lower_level_id]
rate_type_adas = match.groups()[4]
if rate_type_adas == 'EXCIT':
rate_type = 'excitation'
elif rate_type_adas == 'RECOM':
rate_type = 'recombination'
elif rate_type_adas == 'CHEXC':
rate_type = 'thermalcx'
rate_type_adas = match.groups()[4].upper()
if rate_type_adas == "EXCIT":
rate_type = "excitation"
elif rate_type_adas == "RECOM":
rate_type = "recombination"
elif rate_type_adas == "CHEXC":
rate_type = "thermalcx"
else:
raise ValueError("Unrecognised rate type - {}".format(rate_type_adas))

Expand All @@ -255,11 +263,8 @@ def _extract_rate(file, block_num):
# search from start of file
file.seek(0)

wavelength_match = r"^\s*[0-9]*\.[0-9]* ?a? +.*$"
block_id_match = r"^\s*[0-9]*\.[0-9]* ?a?\s*([0-9]*)\s*([0-9]*).*/type *= *([a-zA-Z]*).*/isel *= * ([0-9]*)$"

for block in _group_by_block(file, wavelength_match):
match = re.match(block_id_match, block[0], re.IGNORECASE)
for block in _group_by_block(file, _WAVELENGTH_MATCH):
match = _BLOCK_ID_MATCH.match(block[0])

if not match:
continue
Expand Down Expand Up @@ -311,24 +316,24 @@ def _extract_rate(file, block_num):
density = PerCm3ToPerM3.to(density)
rates = Cm3ToM3.to(rates)

return {'ne': density, 'te': temperature, 'rate': rates}
return {"ne": density, "te": temperature, "rate": rates}

# If code gets to here, block wasn't found.
raise RuntimeError('Block number {} was not found in the ADF15 file.'.format(block_num))
raise RuntimeError("Block number {} was not found in the ADF15 file.".format(block_num))


def _group_by_block(source_file, match_string):
def _group_by_block(source_file, match_pattern):
"""
Generator the splits the ADF15 file into blocks.

Groups lines of file into blocks based on precursor ' 6561.9A 24...'
Groups lines of file into blocks based on wavelength pattern match.

Note: comment section not filtered out of last block, don't over-read!
"""

buffer = []
for line in source_file:
if re.match(match_string, line, re.IGNORECASE):
if match_pattern.match(line):
if buffer:
yield buffer
buffer = [line]
Expand Down
Loading
Loading