File size: 38,680 Bytes
d09f6aa 100024e d09f6aa 100024e d09f6aa 100024e d09f6aa 100024e d09f6aa 100024e d09f6aa 100024e d09f6aa 100024e d09f6aa 100024e d09f6aa 100024e d09f6aa 100024e d09f6aa 100024e d09f6aa 100024e d09f6aa 100024e d09f6aa 100024e d09f6aa 100024e d09f6aa 100024e d09f6aa 100024e d09f6aa 100024e d09f6aa 100024e d09f6aa 100024e d09f6aa 100024e d09f6aa 100024e d09f6aa 100024e d09f6aa 100024e d09f6aa 100024e d09f6aa 100024e d09f6aa 100024e d09f6aa 100024e d09f6aa 100024e d09f6aa 100024e d09f6aa 100024e d09f6aa 100024e d09f6aa 100024e d09f6aa 100024e d09f6aa 100024e d09f6aa 100024e d09f6aa 100024e d09f6aa 100024e d09f6aa 100024e d09f6aa 100024e d09f6aa 100024e d09f6aa 100024e d09f6aa 100024e d09f6aa 100024e d09f6aa 100024e d09f6aa 100024e d09f6aa 100024e d09f6aa 100024e d09f6aa 100024e d09f6aa 100024e d09f6aa 100024e d09f6aa 100024e d09f6aa 100024e d09f6aa 100024e d09f6aa 100024e d09f6aa 100024e d09f6aa 100024e d09f6aa 100024e d09f6aa 100024e d09f6aa 100024e d09f6aa 100024e d09f6aa 100024e d09f6aa 100024e d09f6aa 100024e |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 |
# Module for CSV and APKG export functions
import gradio as gr
import pandas as pd
import genanki
import random
from typing import List, Dict, Any, Optional
import csv
from datetime import datetime
import os
from ankigen_core.utils import get_logger, strip_html_tags
logger = get_logger()
# --- Helper function for formatting fields ---
def _format_field_as_string(value: Any) -> str:
if isinstance(value, list) or isinstance(value, tuple):
return ", ".join(str(item).strip() for item in value if str(item).strip())
if pd.isna(value) or value is None:
return ""
return str(value).strip()
# --- Constants for APKG Generation (Subtask 10) ---
ANKI_BASIC_MODEL_NAME = "AnkiGen Basic"
ANKI_CLOZE_MODEL_NAME = "AnkiGen Cloze"
# It's good practice to generate unique IDs. These are examples.
# Real applications might use a persistent way to store/retrieve these if models are updated.
DEFAULT_BASIC_MODEL_ID = random.randrange(1 << 30, 1 << 31)
DEFAULT_CLOZE_MODEL_ID = random.randrange(1 << 30, 1 << 31)
# --- Full Model Definitions with CSS (Restored) ---
BASIC_MODEL = genanki.Model(
DEFAULT_BASIC_MODEL_ID, # Use the generated ID
ANKI_BASIC_MODEL_NAME, # Use the constant name
fields=[
{"name": "Question"},
{"name": "Answer"},
{"name": "Explanation"},
{"name": "Example"},
{"name": "Prerequisites"},
{"name": "Learning_Outcomes"},
{"name": "Common_Misconceptions"},
{"name": "Difficulty"},
{"name": "SourceURL"}, # Added for consistency if used by template
{"name": "TagsStr"}, # Added for consistency if used by template
],
templates=[
{
"name": "Card 1",
"qfmt": """
<div class=\"card question-side\">
<div class=\"difficulty-indicator {{Difficulty}}\"></div>
<div class=\"content\">
<div class=\"question\">{{Question}}</div>
<div class=\"prerequisites\" onclick=\"event.stopPropagation();\">
<div class=\"prerequisites-toggle\">Show Prerequisites</div>
<div class=\"prerequisites-content\">{{Prerequisites}}</div>
</div>
</div>
</div>
<script>
document.querySelector('.prerequisites-toggle').addEventListener('click', function(e) {
e.stopPropagation();
this.parentElement.classList.toggle('show');
});
</script>
""",
"afmt": """
<div class=\"card answer-side\">
<div class=\"content\">
<div class=\"question-section\">
<div class=\"question\">{{Question}}</div>
<div class=\"prerequisites\">
<strong>Prerequisites:</strong> {{Prerequisites}}
</div>
</div>
<hr>
<div class=\"answer-section\">
<h3>Answer</h3>
<div class=\"answer\">{{Answer}}</div>
</div>
<div class=\"explanation-section\">
<h3>Explanation</h3>
<div class=\"explanation-text\">{{Explanation}}</div>
</div>
<div class=\"example-section\">
<h3>Example</h3>
<div class=\"example-text\">{{Example}}</div>
<!-- Example field might contain pre/code or plain text -->
<!-- Handled by how HTML is put into the Example field -->
</div>
<div class=\"metadata-section\">
<div class=\"learning-outcomes\">
<h3>Learning Outcomes</h3>
<div>{{Learning_Outcomes}}</div>
</div>
<div class=\"misconceptions\">
<h3>Common Misconceptions - Debunked</h3>
<div>{{Common_Misconceptions}}</div>
</div>
<div class=\"difficulty\">
<h3>Difficulty Level</h3>
<div>{{Difficulty}}</div>
</div>
{{#SourceURL}}<div class=\"source-url\"><small>Source: <a href=\"{{SourceURL}}\">{{SourceURL}}</a></small></div>{{/SourceURL}}
</div>
</div>
</div>
""",
}
],
css="""
/* Base styles */
.card {
font-family: 'Inter', system-ui, -apple-system, sans-serif;
font-size: 16px;
line-height: 1.6;
color: #1a1a1a;
max-width: 800px;
margin: 0 auto;
padding: 20px;
background: #ffffff;
}
@media (max-width: 768px) {
.card {
font-size: 14px;
padding: 15px;
}
}
/* Question side */
.question-side {
position: relative;
min-height: 200px;
}
.difficulty-indicator {
position: absolute;
top: 10px;
right: 10px;
width: 10px;
height: 10px;
border-radius: 50%;
}
.difficulty-indicator.beginner { background: #4ade80; }
.difficulty-indicator.intermediate { background: #fbbf24; }
.difficulty-indicator.advanced { background: #ef4444; }
.question {
font-size: 1.3em;
font-weight: 600;
color: #2563eb;
margin-bottom: 1.5em;
}
.prerequisites {
margin-top: 1em;
font-size: 0.9em;
color: #666;
}
.prerequisites-toggle {
color: #2563eb;
cursor: pointer;
text-decoration: underline;
}
.prerequisites-content {
display: none;
margin-top: 0.5em;
padding: 0.5em;
background: #f8fafc;
border-radius: 4px;
}
.prerequisites.show .prerequisites-content {
display: block;
}
/* Answer side */
.answer-section,
.explanation-section,
.example-section {
margin: 1.5em 0;
padding: 1.2em;
border-radius: 8px;
box-shadow: 0 2px 4px rgba(0,0,0,0.05);
}
.answer-section {
background: #f0f9ff;
border-left: 4px solid #2563eb;
}
.explanation-section {
background: #f0fdf4;
border-left: 4px solid #4ade80;
}
.example-section {
background: #fefce8; /* Light yellow */
border-left: 4px solid #facc15; /* Yellow */
}
.example-section pre {
background-color: #2d2d2d; /* Darker background for code blocks */
color: #f8f8f2; /* Light text for contrast */
padding: 1em;
border-radius: 0.3em;
overflow-x: auto; /* Horizontal scroll for long lines */
font-family: 'Consolas', 'Monaco', 'Menlo', monospace;
font-size: 0.9em;
line-height: 1.4;
}
.example-section code {
font-family: 'Consolas', 'Monaco', 'Menlo', monospace;
}
.metadata-section {
margin-top: 2em;
padding-top: 1em;
border-top: 1px solid #e5e7eb; /* Light gray border */
font-size: 0.9em;
color: #4b5563; /* Cool gray */
}
.metadata-section h3 {
font-size: 1em;
color: #1f2937; /* Darker gray for headings */
margin-bottom: 0.5em;
}
.metadata-section > div {
margin-bottom: 0.8em;
}
.source-url a {
color: #2563eb;
text-decoration: none;
}
.source-url a:hover {
text-decoration: underline;
}
/* Styles for cloze deletion cards */
.cloze {
font-weight: bold;
color: blue;
}
.nightMode .cloze {
color: lightblue;
}
/* General utility */
hr {
border: none;
border-top: 1px dashed #cbd5e1; /* Light dashed line */
margin: 1.5em 0;
}
/* Rich text field styling (if Anki adds classes for these) */
.field ul, .field ol {
margin-left: 1.5em;
padding-left: 0.5em;
}
.field li {
margin-bottom: 0.3em;
}
/* Responsive design */
@media (max-width: 640px) {
.answer-section,
.explanation-section,
.example-section {
padding: 1em;
margin: 1em 0;
}
}
/* Animations */
@keyframes fadeIn {
from { opacity: 0; }
to { opacity: 1; }
}
.card {
animation: fadeIn 0.3s ease-in-out;
}
""",
# model_type=genanki.Model.BASIC, # This was still incorrect
# No model_type needed, defaults to Basic (0)
)
CLOZE_MODEL = genanki.Model(
DEFAULT_CLOZE_MODEL_ID, # Use the generated ID
ANKI_CLOZE_MODEL_NAME, # Use the constant name
fields=[
{"name": "Text"},
{"name": "Back Extra"},
{"name": "Explanation"},
{"name": "Example"},
{"name": "Prerequisites"},
{"name": "Learning_Outcomes"},
{"name": "Common_Misconceptions"},
{"name": "Difficulty"},
{"name": "SourceURL"},
{"name": "TagsStr"},
],
templates=[
{
"name": "Cloze Card",
"qfmt": """
<div class=\"card question-side\">
<div class=\"difficulty-indicator {{Difficulty}}\"></div>
<div class=\"content\">
<div class=\"question\">{{cloze:Text}}</div>
<div class=\"prerequisites\" onclick=\"event.stopPropagation();\">
<div class=\"prerequisites-toggle\">Show Prerequisites</div>
<div class=\"prerequisites-content\">{{Prerequisites}}</div>
</div>
</div>
</div>
<script>
document.querySelector('.prerequisites-toggle').addEventListener('click', function(e) {
e.stopPropagation();
this.parentElement.classList.toggle('show');
});
</script>
""",
"afmt": """
<div class=\"card answer-side\">
<div class=\"content\">
<div class=\"question-section\">
<div class=\"question\">{{cloze:Text}}</div>
<div class=\"prerequisites\">
<strong>Prerequisites:</strong> {{Prerequisites}}
</div>
</div>
<hr>
{{#Back Extra}}
<div class=\"back-extra-section\">
<h3>Additional Information</h3>
<div class=\"back-extra-text\">{{Back Extra}}</div>
</div>
{{/Back Extra}}
<div class=\"explanation-section\">
<h3>Explanation</h3>
<div class=\"explanation-text\">{{Explanation}}</div>
</div>
<div class=\"example-section\">
<h3>Example</h3>
<div class=\"example-text\">{{Example}}</div>
</div>
<div class=\"metadata-section\">
<div class=\"learning-outcomes\">
<h3>Learning Outcomes</h3>
<div>{{Learning_Outcomes}}</div>
</div>
<div class=\"misconceptions\">
<h3>Common Misconceptions - Debunked</h3>
<div>{{Common_Misconceptions}}</div>
</div>
<div class=\"difficulty\">
<h3>Difficulty Level</h3>
<div>{{Difficulty}}</div>
</div>
{{#SourceURL}}<div class=\"source-url\"><small>Source: <a href=\"{{SourceURL}}\">{{SourceURL}}</a></small></div>{{/SourceURL}}
</div>
</div>
</div>
""",
}
],
css="""
/* Base styles */
.card {
font-family: 'Inter', system-ui, -apple-system, sans-serif;
font-size: 16px;
line-height: 1.6;
color: #1a1a1a;
max-width: 800px;
margin: 0 auto;
padding: 20px;
background: #ffffff;
}
@media (max-width: 768px) {
.card {
font-size: 14px;
padding: 15px;
}
}
/* Question side */
.question-side {
position: relative;
min-height: 200px;
}
.difficulty-indicator {
position: absolute;
top: 10px;
right: 10px;
width: 10px;
height: 10px;
border-radius: 50%;
}
.difficulty-indicator.beginner { background: #4ade80; }
.difficulty-indicator.intermediate { background: #fbbf24; }
.difficulty-indicator.advanced { background: #ef4444; }
.question {
font-size: 1.3em;
font-weight: 600;
color: #2563eb;
margin-bottom: 1.5em;
}
.prerequisites {
margin-top: 1em;
font-size: 0.9em;
color: #666;
}
.prerequisites-toggle {
color: #2563eb;
cursor: pointer;
text-decoration: underline;
}
.prerequisites-content {
display: none;
margin-top: 0.5em;
padding: 0.5em;
background: #f8fafc;
border-radius: 4px;
}
.prerequisites.show .prerequisites-content {
display: block;
}
/* Answer side */
.answer-section,
.explanation-section,
.example-section {
margin: 1.5em 0;
padding: 1.2em;
border-radius: 8px;
box-shadow: 0 2px 4px rgba(0,0,0,0.05);
}
.answer-section { /* Shared with question for cloze, but can be general */
background: #f0f9ff;
border-left: 4px solid #2563eb;
}
.back-extra-section {
background: #eef2ff; /* A slightly different shade for additional info */
border-left: 4px solid #818cf8; /* Indigo variant */
margin: 1.5em 0;
padding: 1.2em;
border-radius: 8px;
box-shadow: 0 2px 4px rgba(0,0,0,0.05);
}
.explanation-section {
background: #f0fdf4;
border-left: 4px solid #4ade80;
}
.example-section {
background: #fefce8; /* Light yellow */
border-left: 4px solid #facc15; /* Yellow */
}
.example-section pre {
background-color: #2d2d2d; /* Darker background for code blocks */
color: #f8f8f2; /* Light text for contrast */
padding: 1em;
border-radius: 0.3em;
overflow-x: auto; /* Horizontal scroll for long lines */
font-family: 'Consolas', 'Monaco', 'Menlo', monospace;
font-size: 0.9em;
line-height: 1.4;
}
.example-section code {
font-family: 'Consolas', 'Monaco', 'Menlo', monospace;
}
.metadata-section {
margin-top: 2em;
padding-top: 1em;
border-top: 1px solid #e5e7eb; /* Light gray border */
font-size: 0.9em;
color: #4b5563; /* Cool gray */
}
.metadata-section h3 {
font-size: 1em;
color: #1f2937; /* Darker gray for headings */
margin-bottom: 0.5em;
}
.metadata-section > div {
margin-bottom: 0.8em;
}
.source-url a {
color: #2563eb;
text-decoration: none;
}
.source-url a:hover {
text-decoration: underline;
}
/* Styles for cloze deletion cards */
.cloze {
font-weight: bold;
color: blue;
}
.nightMode .cloze {
color: lightblue;
}
/* General utility */
hr {
border: none;
border-top: 1px dashed #cbd5e1; /* Light dashed line */
margin: 1.5em 0;
}
/* Rich text field styling (if Anki adds classes for these) */
.field ul, .field ol {
margin-left: 1.5em;
padding-left: 0.5em;
}
.field li {
margin-bottom: 0.3em;
}
""",
# model_type=genanki.Model.CLOZE, # This was still incorrect
model_type=1, # Corrected to use integer 1 for Cloze
)
# --- Helper functions for APKG (Subtask 10) ---
def _get_or_create_model(
model_id: int,
name: str,
fields: List[Dict[str, str]],
templates: List[Dict[str, str]],
) -> genanki.Model:
return genanki.Model(model_id, name, fields=fields, templates=templates)
# --- New CSV Exporter for List of Dictionaries ---
def export_cards_to_csv(
cards: List[Dict[str, Any]], filename: Optional[str] = None
) -> str:
"""Export a list of card dictionaries to a CSV file.
Args:
cards: A list of dictionaries, where each dictionary represents a card
and should contain 'front' and 'back' keys. Other keys like
'tags' and 'note_type' are optional.
filename: Optional. The desired filename/path for the CSV.
If None, a timestamped filename will be generated.
Returns:
The path to the generated CSV file.
Raises:
IOError: If there is an issue writing to the file.
KeyError: If a card dictionary is missing essential keys like 'front' or 'back'.
ValueError: If the cards list is empty or not provided.
"""
if not cards:
logger.warning("export_cards_to_csv called with an empty list of cards.")
raise ValueError("No cards provided to export.")
if not filename:
timestamp = datetime.now().strftime("%Y%m%d_%H%M%S")
# Ensure filename is just the name, not a path if not intended
# For simplicity, this example saves in the current working directory if no path is specified.
filename = f"ankigen_cards_{timestamp}.csv"
logger.info(f"No filename provided, generated: {filename}")
# Define the fieldnames expected in the CSV.
# 'front' and 'back' are mandatory.
fieldnames = ["front", "back", "tags", "note_type"]
try:
logger.info(f"Attempting to export {len(cards)} cards to {filename}")
with open(filename, "w", newline="", encoding="utf-8") as csvfile:
writer = csv.DictWriter(
csvfile, fieldnames=fieldnames, extrasaction="ignore"
)
writer.writeheader()
for i, card in enumerate(cards):
try:
# Ensure mandatory fields exist, others are optional via card.get in row_to_write
if "front" not in card or "back" not in card:
raise KeyError(
f"Card at index {i} is missing 'front' or 'back' key."
)
row_to_write = {
"front": card["front"],
"back": card["back"],
"tags": card.get("tags", ""),
"note_type": card.get("note_type", "Basic"),
}
writer.writerow(row_to_write)
except KeyError as e_inner:
logger.error(
f"Skipping card due to KeyError: {e_inner}. Card data: {card}"
)
# Optionally re-raise if one bad card should stop the whole export,
# or continue to export valid cards.
# For this implementation, we log and continue.
continue
logger.info(f"Successfully exported cards to {filename}")
return filename
except IOError as e_io:
logger.error(f"IOError during CSV export to {filename}: {e_io}", exc_info=True)
raise # Re-raise the IOError
except Exception as e_general: # Catch any other unexpected errors
logger.error(
f"Unexpected error during CSV export to {filename}: {e_general}",
exc_info=True,
)
raise
def export_cards_to_apkg(
cards: List[Dict[str, Any]],
filename: Optional[str] = None,
deck_name: str = "Ankigen Generated Cards",
) -> str:
"""Exports a list of card dictionaries to an Anki .apkg file.
Args:
cards: List of dictionaries, where each dictionary represents a card.
It's expected that these dicts are prepared by export_dataframe_to_apkg
and contain keys like 'Question', 'Answer', 'Explanation', etc.
filename: The full path (including filename) for the exported file.
If None, a default filename will be generated in the current directory.
deck_name: The name of the deck if exporting to .apkg format.
Returns:
The path to the exported file.
"""
logger.info(f"Starting APKG export for {len(cards)} cards to deck '{deck_name}'.")
if not filename:
timestamp = datetime.now().strftime("%Y%m%d_%H%M%S")
filename = f"ankigen_deck_{timestamp}.apkg"
elif not filename.lower().endswith(".apkg"):
filename += ".apkg"
output_dir = os.path.dirname(filename)
if output_dir and not os.path.exists(output_dir):
os.makedirs(output_dir)
logger.info(f"Created output directory for APKG: {output_dir}")
anki_basic_model = BASIC_MODEL
anki_cloze_model = CLOZE_MODEL
deck_id = random.randrange(1 << 30, 1 << 31)
anki_deck = genanki.Deck(deck_id, deck_name)
notes_added_count = 0
for card_dict in cards:
note_type = card_dict.get("note_type", "Basic")
tags_for_note_object = card_dict.get("tags_for_note_object", [])
# Extract all potential fields, defaulting to empty strings
question = card_dict.get("Question", "")
answer = card_dict.get("Answer", "")
explanation = card_dict.get("Explanation", "")
example = card_dict.get("Example", "")
prerequisites = card_dict.get("Prerequisites", "")
learning_outcomes = card_dict.get("Learning_Outcomes", "")
common_misconceptions = card_dict.get("Common_Misconceptions", "")
difficulty = card_dict.get("Difficulty", "")
source_url = card_dict.get("SourceURL", "")
tags_str_field = card_dict.get(
"TagsStr", ""
) # This is the string for the model's TagsStr field
# The 'Question' field from card_dict is used as the main text for both basic and cloze.
# For cloze, this 'Question' field should contain the cloze-formatted text (e.g., "The capital of {{c1::France}} is Paris.")
if not question:
logger.error(
f"SKIPPING CARD DUE TO EMPTY 'Question' (front/text) field. Card data: {card_dict}"
)
continue
try:
if note_type.lower() == "cloze":
# CLOZE_MODEL fields: Text, Back Extra, Explanation, Example, Prerequisites,
# Learning_Outcomes, Common_Misconceptions, Difficulty, SourceURL, TagsStr
note_fields = [
question, # Text (this is the card_dict['Question'] which should be cloze-formatted)
answer, # Back Extra (this is card_dict['Answer'])
explanation,
example,
prerequisites,
learning_outcomes,
common_misconceptions,
difficulty,
source_url,
tags_str_field,
]
note = genanki.Note(
model=anki_cloze_model,
fields=note_fields,
tags=tags_for_note_object,
)
else: # Basic
# BASIC_MODEL fields: Question, Answer, Explanation, Example, Prerequisites,
# Learning_Outcomes, Common_Misconceptions, Difficulty, SourceURL, TagsStr
note_fields = [
question,
answer,
explanation,
example,
prerequisites,
learning_outcomes,
common_misconceptions,
difficulty,
source_url,
tags_str_field,
]
note = genanki.Note(
model=anki_basic_model,
fields=note_fields,
tags=tags_for_note_object,
)
anki_deck.add_note(note)
notes_added_count += 1
except Exception as e:
logger.error(
f"Failed to create genanki.Note for card: {card_dict}. Error: {e}",
exc_info=True,
)
logger.warning(f"Skipping card due to error: Question='{question[:50]}...'")
if notes_added_count == 0 and cards: # Some cards were provided but none were added
logger.error( # Changed to error for more visibility
"No valid notes could be created from the provided cards. APKG generation aborted."
)
# This error should be caught by the calling function in app.py to inform the user
raise gr.Error("Failed to create any valid Anki notes from the input.")
elif not cards: # No cards provided initially
logger.info("No cards provided to export to APKG. APKG generation skipped.")
# Depending on desired behavior, could raise or return a specific status/filename
# For now, let's assume an empty/default filename or None indicates no action if no cards
# However, the function is typed to return str, so raising is more consistent if no file is made.
raise gr.Error("No cards were provided to generate an APKG file.")
else: # notes_added_count > 0
logger.info(
f"Added {notes_added_count} notes to deck '{deck_name}'. Proceeding to package."
)
# Only proceed to package and write if notes were successfully added
package = genanki.Package(anki_deck)
try:
package.write_to_file(filename)
logger.info(f"Successfully exported Anki deck to {filename}")
except Exception as e:
logger.error(f"Failed to write .apkg file to {filename}: {e}", exc_info=True)
raise IOError(f"Could not write .apkg file: {e}")
return filename
def export_cards_from_crawled_content(
cards: List[Dict[str, Any]],
output_path: Optional[
str
] = None, # Changed from filename to output_path for clarity
export_format: str = "csv", # Added export_format parameter
deck_name: str = "Ankigen Generated Cards",
) -> str:
"""Exports cards (list of dicts) to the specified format (CSV or APKG).
Args:
cards: List of dictionaries, where each dictionary represents a card.
Expected keys: 'front', 'back'. Optional: 'tags' (space-separated string), 'source_url', 'note_type' ('Basic' or 'Cloze').
output_path: The full path (including filename) for the exported file.
If None, a default filename will be generated in the current directory.
export_format: The desired format, either 'csv' or 'apkg'.
deck_name: The name of the deck if exporting to .apkg format.
Returns:
The path to the exported file.
"""
if not cards:
logger.warning("No cards provided to export_cards_from_crawled_content.")
# MODIFIED: Raise error immediately if no cards, as per test expectation
raise ValueError("No cards provided to export.")
logger.info(
f"Exporting {len(cards)} cards to format '{export_format}' with deck name '{deck_name}'."
)
if export_format.lower() == "csv":
return export_cards_to_csv(cards, filename=output_path)
elif export_format.lower() == "apkg":
return export_cards_to_apkg(cards, filename=output_path, deck_name=deck_name)
else:
supported_formats = ["csv", "apkg"]
logger.error(
f"Unsupported export format: {export_format}. Supported formats: {supported_formats}"
)
# MODIFIED: Updated error message to include supported formats
raise ValueError(
f"Unsupported export format: {export_format}. Supported formats: {supported_formats}"
)
# --- New DataFrame CSV Exporter (Subtask 11) ---
def export_dataframe_to_csv(
data: Optional[pd.DataFrame],
filename_suggestion: Optional[str] = "ankigen_cards.csv",
) -> Optional[str]:
"""Exports a Pandas DataFrame to a CSV file, designed for Gradio download.
Args:
data: The Pandas DataFrame to export.
filename_suggestion: A suggestion for the base filename (e.g., from subject).
Returns:
The path to the temporary CSV file, or None if an error occurs or data is empty.
"""
logger.info(
f"Attempting to export DataFrame to CSV. Suggested filename: {filename_suggestion}"
)
if data is None or data.empty:
logger.warning(
"No data provided to export_dataframe_to_csv. Skipping CSV export."
)
raise gr.Error(
"No card data available"
) # Notify user via Gradio with Error instead of Info
# return None # This line is now unreachable due to the raise
try:
# Create a specific filename using both suggestion and timestamp
timestamp = datetime.now().strftime("%Y%m%d_%H%M%S")
base_name_from_suggestion = "ankigen_cards" # Default base part
# Sanitize and use the suggestion (e.g., subject name) if provided
if filename_suggestion and isinstance(filename_suggestion, str):
# Remove .csv if present, then sanitize
processed_suggestion = filename_suggestion.removesuffix(".csv")
safe_suggestion = (
processed_suggestion.replace(" ", "_")
.replace("/", "-")
.replace("\\\\", "-")
)
if (
safe_suggestion
): # If suggestion wasn't just '.csv' or empty after processing
base_name_from_suggestion = f"ankigen_{safe_suggestion[:50]}"
# If suggestion was empty or only '.csv', default base_name_from_suggestion remains 'ankigen_cards'
final_filename = f"{base_name_from_suggestion}_{timestamp}.csv"
# Ensure output directory exists if filename contains path
output_dir = os.path.dirname(final_filename)
if output_dir and not os.path.exists(output_dir):
os.makedirs(output_dir)
logger.info(f"Created output directory for CSV: {output_dir}")
data.to_csv(final_filename, index=False) # MODIFIED: Write to final_filename
logger.info(f"Successfully exported DataFrame to CSV: {final_filename}")
gr.Info(
f"CSV ready for download: {os.path.basename(final_filename)}"
) # User-friendly message
return final_filename # MODIFIED: Return final_filename
except Exception as e:
logger.error(f"Error exporting DataFrame to CSV: {e}", exc_info=True)
gr.Error(f"Error exporting DataFrame to CSV: {e}")
return None
# --- New DataFrame to APKG Exporter (for Main Generator Tab) ---
def export_dataframe_to_apkg(
df: pd.DataFrame,
output_path: Optional[str],
deck_name: str,
) -> str:
"""Exports a DataFrame of cards to an Anki .apkg file."""
if df.empty:
logger.warning("export_dataframe_to_apkg called with an empty DataFrame.")
raise ValueError("No cards in DataFrame to export.")
logger.info(
f"Starting APKG export for DataFrame with {len(df)} rows to deck '{deck_name}'. Output: {output_path}"
)
cards_for_apkg: List[Dict[str, Any]] = []
for _, row in df.iterrows():
try:
note_type_val = (
_format_field_as_string(row.get("Card_Type", "Basic")) or "Basic"
)
topic = _format_field_as_string(row.get("Topic", ""))
difficulty_raw = _format_field_as_string(row.get("Difficulty", ""))
difficulty_plain_for_tag = strip_html_tags(
difficulty_raw
) # Strip HTML for the tag
tags_list_for_note_obj = [] # For genanki.Note(tags=...)
if topic:
tags_list_for_note_obj.append(topic.replace(" ", "_").replace(",", "_"))
if difficulty_plain_for_tag: # Use the plain text version for the tag
# Further sanitize for Anki tags: replace spaces with underscores, remove other invalid chars if any.
# Anki tags also often don't like colons or other special chars except underscore/hyphen.
# For now, just replacing space, as that's the error seen.
safe_difficulty_tag = difficulty_plain_for_tag.replace(" ", "_")
tags_list_for_note_obj.append(safe_difficulty_tag)
tags_str_for_field = " ".join(
tags_list_for_note_obj
) # For the 'TagsStr' model field
# Prepare a dictionary that contains all possible fields our models might need.
card_data_for_note = {
"note_type": note_type_val,
"tags_for_note_object": tags_list_for_note_obj,
"TagsStr": tags_str_for_field,
"Question": _format_field_as_string(row.get("Question", "")),
"Answer": _format_field_as_string(row.get("Answer", "")),
"Explanation": _format_field_as_string(row.get("Explanation", "")),
"Example": _format_field_as_string(row.get("Example", "")),
"Prerequisites": _format_field_as_string(row.get("Prerequisites", "")),
"Learning_Outcomes": _format_field_as_string(
row.get("Learning_Outcomes", "")
),
"Common_Misconceptions": _format_field_as_string(
row.get("Common_Misconceptions", "")
),
"Difficulty": difficulty_raw, # Keep the original HTML for the 'Difficulty' field itself
"SourceURL": _format_field_as_string(row.get("Source_URL", "")),
}
cards_for_apkg.append(card_data_for_note)
except Exception as e:
logger.error(
f"Error processing DataFrame row for APKG: {row}. Error: {e}",
exc_info=True,
)
continue
if not cards_for_apkg:
logger.error("No cards could be processed from DataFrame for APKG export.")
raise ValueError("No processable cards found in DataFrame for APKG export.")
return export_cards_to_apkg(
cards_for_apkg, filename=output_path, deck_name=deck_name
)
# --- Compatibility Exports for Tests and Legacy Code ---
# These aliases ensure that tests expecting these names will find them.
# Export functions under expected names
export_csv = (
export_dataframe_to_csv # Update this to export_dataframe_to_csv for compatibility
)
# MODIFIED: export_deck is now a wrapper to provide a default deck_name
def export_deck(
df: pd.DataFrame,
output_path: Optional[str] = None,
deck_name: str = "Ankigen Generated Cards",
) -> str:
"""Alias for exporting a DataFrame to APKG, providing a default deck name."""
if df is None or df.empty:
logger.warning("export_deck called with None or empty DataFrame.")
# Match the error type and message expected by tests
raise gr.Error("No card data available")
# Original logic to call export_dataframe_to_apkg
# Ensure all necessary parameters for export_dataframe_to_apkg are correctly passed.
# The export_dataframe_to_apkg function itself will handle its specific error conditions.
# The 'output_path' for export_dataframe_to_apkg needs to be handled.
# If 'output_path' is None here, export_cards_to_apkg (called by export_dataframe_to_apkg)
# will generate a default filename.
# If output_path is not provided to export_deck, it's None.
# export_dataframe_to_apkg expects output_path: Optional[str].
# And export_cards_to_apkg (which it calls) also handles Optional[str] filename.
# So, passing output_path directly should be fine.
return export_dataframe_to_apkg(df, output_path=output_path, deck_name=deck_name)
export_dataframe_csv = export_dataframe_to_csv
export_dataframe_apkg = export_dataframe_to_apkg
__all__ = [
"BASIC_MODEL",
"CLOZE_MODEL",
"export_csv",
"export_deck",
"export_dataframe_csv",
"export_dataframe_apkg",
"export_cards_to_csv",
"export_cards_to_apkg",
"export_cards_from_crawled_content",
"export_dataframe_to_csv",
"export_dataframe_to_apkg",
]
|