diff --git a/CHANGELOG.md b/CHANGELOG.md index 020619e584..664879701f 100644 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -1,4 +1,4 @@ -## 0.16.1-dev2 +## 0.16.1-dev3 ### Enhancements @@ -11,6 +11,7 @@ * **Minify text_as_html from DOCX.** Previously `.metadata.text_as_html` for DOCX tables was "bloated" with whitespace and noise elements introduced by `tabulate` that produced over-chunking and lower "semantic density" of elements. Reduce HTML to minimum character count without preserving all text. * **Fall back to filename extension-based file-type detection for unidentified OLE files.** Resolves a problem where a DOC file that could not be detected as such by `filetype` was incorrectly identified as a MSG file. * **Minify text_as_html from XLSX.** Previously `.metadata.text_as_html` for DOCX tables was "bloated" with whitespace and noise elements introduced by `pandas` that produced over-chunking and lower "semantic density" of elements. Reduce HTML to minimum character count without preserving all text. +* **Minify text_as_html from CSV.** Previously `.metadata.text_as_html` for CSV tables was "bloated" with whitespace and noise elements introduced by `pandas` that produced over-chunking and lower "semantic density" of elements. Reduce HTML to minimum character count without preserving all text. ## 0.16.0 diff --git a/test_unstructured/partition/test_constants.py b/test_unstructured/partition/test_constants.py index 8b003cd9c5..a7b0ddce81 100644 --- a/test_unstructured/partition/test_constants.py +++ b/test_unstructured/partition/test_constants.py @@ -1,32 +1,32 @@ -EXPECTED_TABLE = """
Stanley Cups | -- | - |
Team | -Location | -Stanley Cups | -
Blues | -STL | -1 | -
Flyers | -PHI | -2 | -
Maple Leafs | -TOR | -13 | -
Stanley Cups | ||
Team | Location | Stanley Cups |
Blues | STL | 1 |
Flyers | PHI | 2 |
Maple Leafs | TOR | 13 |
Year | Month | Revenue | Costs | |
2022 | 1 | 123 | -123 | |
2023 | 2 | 143,1 | -814,38 | |
2024 | 3 | 215,32 | -11,08 |
Stanley Cups | ||
Team | Location | Stanley Cups |
Blues | STL | 1 |
Flyers | PHI | 2 |
Maple Leafs | TOR | 13 |
👨\\U+1F3FB🔧 | TOR | 15 |
Year | -Month | -Revenue | -Costs | -- |
2022 | -1 | -123 | --123 | -- |
2023 | -2 | -143,1 | --814,38 | -- |
2024 | -3 | -215,32 | --11,08 | -- |
Stanley Cups | -- | - |
Team | -Location | -Stanley Cups | -
Blues | -STL | -1 | -
Flyers | -PHI | -2 | -
Maple Leafs | -TOR | -13 | -
👨\\U+1F3FB🔧 | -TOR | -15 | -
MC | " diff --git a/test_unstructured/partition/test_csv.py b/test_unstructured/partition/test_csv.py index 9317bec8cb..e3c34edbf5 100644 --- a/test_unstructured/partition/test_csv.py +++ b/test_unstructured/partition/test_csv.py @@ -200,11 +200,8 @@ def test_partition_csv_header(): ) table = elements[0] - assert clean_extra_whitespace(table.text) == ( - "Stanley Cups Unnamed: 1 Unnamed: 2 " + EXPECTED_TEXT_XLSX - ) + assert table.text == "Stanley Cups Unnamed: 1 Unnamed: 2 " + EXPECTED_TEXT_XLSX assert table.metadata.text_as_html is not None - assert "" in table.metadata.text_as_html # ================================================================================================ diff --git a/test_unstructured/partition/test_tsv.py b/test_unstructured/partition/test_tsv.py index 5bd4ef4926..5276e6006d 100644 --- a/test_unstructured/partition/test_tsv.py +++ b/test_unstructured/partition/test_tsv.py @@ -14,7 +14,6 @@ ) from test_unstructured.unit_utils import assert_round_trips_through_JSON, example_doc_path from unstructured.chunking.title import chunk_by_title -from unstructured.cleaners.core import clean_extra_whitespace from unstructured.documents.elements import Table from unstructured.partition.tsv import partition_tsv @@ -31,11 +30,11 @@ def test_partition_tsv_from_filename(filename: str, expected_text: str, expected_table: str): elements = partition_tsv(example_doc_path(filename), include_header=False) - assert clean_extra_whitespace(elements[0].text) == expected_text - assert elements[0].metadata.text_as_html == expected_table - assert elements[0].metadata.filetype == EXPECTED_FILETYPE - for element in elements: - assert element.metadata.filename == filename + table = elements[0] + assert table.text == expected_text + assert table.metadata.text_as_html == expected_table + assert table.metadata.filetype == EXPECTED_FILETYPE + assert all(e.metadata.filename == filename for e in elements) def test_partition_tsv_from_filename_with_metadata_filename(): @@ -43,9 +42,8 @@ def test_partition_tsv_from_filename_with_metadata_filename(): example_doc_path("stanley-cups.tsv"), metadata_filename="test", include_header=False ) - assert clean_extra_whitespace(elements[0].text) == EXPECTED_TEXT - for element in elements: - assert element.metadata.filename == "test" + assert elements[0].text == EXPECTED_TEXT + assert all(e.metadata.filename == "test" for e in elements) @pytest.mark.parametrize( @@ -59,21 +57,20 @@ def test_partition_tsv_from_file(filename: str, expected_text: str, expected_tab with open(example_doc_path(filename), "rb") as f: elements = partition_tsv(file=f, include_header=False) - assert clean_extra_whitespace(elements[0].text) == expected_text - assert isinstance(elements[0], Table) - assert elements[0].metadata.text_as_html == expected_table - assert elements[0].metadata.filetype == EXPECTED_FILETYPE - for element in elements: - assert element.metadata.filename is None + table = elements[0] + assert isinstance(table, Table) + assert table.text == expected_text + assert table.metadata.text_as_html == expected_table + assert table.metadata.filetype == EXPECTED_FILETYPE + assert all(e.metadata.filename is None for e in elements) def test_partition_tsv_from_file_with_metadata_filename(): with open(example_doc_path("stanley-cups.tsv"), "rb") as f: elements = partition_tsv(file=f, metadata_filename="test", include_header=False) - assert clean_extra_whitespace(elements[0].text) == EXPECTED_TEXT - for element in elements: - assert element.metadata.filename == "test" + assert elements[0].text == EXPECTED_TEXT + assert all(element.metadata.filename == "test" for element in elements) # -- .metadata.last_modified --------------------------------------------------------------------- @@ -142,12 +139,10 @@ def test_partition_tsv_header(): example_doc_path("stanley-cups.tsv"), strategy="fast", include_header=True ) - e = elements[0] - assert ( - clean_extra_whitespace(e.text) == "Stanley Cups Unnamed: 1 Unnamed: 2 " + EXPECTED_TEXT_XLSX - ) - assert e.metadata.text_as_html is not None - assert "" in e.metadata.text_as_html + table = elements[0] + assert table.text == "Stanley Cups Unnamed: 1 Unnamed: 2 " + EXPECTED_TEXT_XLSX + assert table.metadata.text_as_html is not None + assert "
Release Year | \nTitle | \nOrigin/Ethnicity | \nDirector | \nCast | \nGenre | \nWiki Page | \nPlot | \n
1901 | \nKansas Saloon Smashers | \nAmerican | \nUnknown | \n\n | unknown | \nhttps://en.wikipedia.org/wiki/Kansas_Saloon_Smashers | \nA bartender is working at a saloon, serving drinks to customers. After he fills a stereotypically Irish man's bucket with beer, Carrie Nation and her followers burst inside. They assault the Irish man, pulling his hat over his eyes and then dumping the beer over his head. The group then begin wrecking the bar, smashing the fixtures, mirrors, and breaking the cash register. The bartender then sprays seltzer water in Nation's face before a group of policemen appear and order everybody to leave.[1] | \n
1901 | \nLove by the Light of the Moon | \nAmerican | \nUnknown | \n\n | unknown | \nhttps://en.wikipedia.org/wiki/Love_by_the_Light_of_the_Moon | \nThe moon, painted with a smiling face hangs over a park at night. A young couple walking past a fence learn on a railing and look up. The moon smiles. They embrace, and the moon's smile gets bigger. They then sit down on a bench by a tree. The moon's view is blocked, causing him to frown. In the last scene, the man fans the woman with his hat because the moon has left the sky and is perched over her shoulder to see everything better. | \n
1901 | \nThe Martyred Presidents | \nAmerican | \nUnknown | \n\n | unknown | \nhttps://en.wikipedia.org/wiki/The_Martyred_Presidents | \nThe film, just over a minute long, is composed of two shots. In the first, a girl sits at the base of an altar or tomb, her face hidden from the camera. At the center of the altar, a viewing portal displays the portraits of three U.S. Presidents\u2014Abraham Lincoln, James A. Garfield, and William McKinley\u2014each victims of assassination.\\r\\nIn the second shot, which runs just over eight seconds long, an assassin kneels feet of Lady Justice. | \n
1901 | \nTerrible Teddy, the Grizzly King | \nAmerican | \nUnknown | \n\n | unknown | \nhttps://en.wikipedia.org/wiki/Terrible_Teddy,_the_Grizzly_King | \nLasting just 61 seconds and consisting of two shots, the first shot is set in a wood during winter. The actor representing then vice-president Theodore Roosevelt enthusiastically hurries down a hillside towards a tree in the foreground. He falls once, but rights himself and cocks his rifle. Two other men, bearing signs reading \"His Photographer\" and \"His Press Agent\" respectively, follow him into the shot; the photographer sets up his camera. \"Teddy\" aims his rifle upward at the tree and fells what appears to be a common house cat, which he then proceeds to stab. \"Teddy\" holds his prize aloft, and the press agent takes notes. The second shot is taken in a slightly different part of the wood, on a path. \"Teddy\" rides the path on his horse towards the camera and out to the left of the shot, followed closely by the press agent and photographer, still dutifully holding their signs. | \n
1902 | \nJack and the Beanstalk | \nAmerican | \nGeorge S. Fleming, Edwin S. Porter | \n\n | unknown | \nhttps://en.wikipedia.org/wiki/Jack_and_the_Beanstalk_(1902_film) | \nThe earliest known adaptation of the classic fairytale, this films shows Jack trading his cow for the beans, his mother forcing him to drop them in the front yard, and beig forced upstairs. As he sleeps, Jack is visited by a fairy who shows him glimpses of what will await him when he ascends the bean stalk. In this version, Jack is the son of a deposed king. When Jack wakes up, he finds the beanstalk has grown and he climbs to the top where he enters the giant's home. The giant finds Jack, who narrowly escapes. The giant chases Jack down the bean stalk, but Jack is able to cut it down before the giant can get to safety. He falls and is killed as Jack celebrates. The fairy then reveals that Jack may return home as a prince. | \n
1903 | \nAlice in Wonderland | \nAmerican | \nCecil Hepworth | \nMay Clark | \nunknown | \nhttps://en.wikipedia.org/wiki/Alice_in_Wonderland_(1903_film) | \nAlice follows a large white rabbit down a \"Rabbit-hole\". She finds a tiny door. When she finds a bottle labeled \"Drink me\", she does, and shrinks, but not enough to pass through the door. She then eats something labeled \"Eat me\" and grows larger. She finds a fan when enables her to shrink enough to get into the \"Garden\" and try to get a \"Dog\" to play with her. She enters the \"White Rabbit's tiny House,\" but suddenly resumes her normal size. In order to get out, she has to use the \"magic fan.\"\\r\\nShe enters a kitchen, in which there is a cook and a woman holding a baby. She persuades the woman to give her the child and takes the infant outside after the cook starts throwing things around. The baby then turns into a pig and squirms out of her grip. \"The Duchess's Cheshire Cat\" appears and disappears a couple of times to Alice and directs her to the Mad Hatter's \"Mad Tea-Party.\" After a while, she leaves.\\r\\nThe Queen invites Alice to join the \"ROYAL PROCESSION\": a parade of marching playing cards and others headed by the White Rabbit. When Alice \"unintentionally offends the Queen\", the latter summons the \"Executioner\". Alice \"boxes the ears\", then flees when all the playing cards come for her. Then she wakes up and realizes it was all a dream. | \n
1903 | \nThe Great Train Robbery | \nAmerican | \nEdwin S. Porter | \n\n | western | \nhttps://en.wikipedia.org/wiki/The_Great_Train_Robbery_(1903_film) | \nThe film opens with two bandits breaking into a railroad telegraph office, where they force the operator at gunpoint to have a train stopped and to transmit orders for the engineer to fill the locomotive's tender at the station's water tank. They then knock the operator out and tie him up. As the train stops it is boarded by the bandits\u200d\u2014\u200cnow four. Two bandits enter an express car, kill a messenger and open a box of valuables with dynamite; the others kill the fireman and force the engineer to halt the train and disconnect the locomotive. The bandits then force the passengers off the train and rifle them for their belongings. One passenger tries to escape but is instantly shot down. Carrying their loot, the bandits escape in the locomotive, later stopping in a valley where their horses had been left.\\r\\nMeanwhile, back in the telegraph office, the bound operator awakens, but he collapses again. His daughter arrives bringing him his meal and cuts him free, and restores him to consciousness by dousing him with water.\\r\\nThere is some comic relief at a dance hall, where an Eastern stranger is forced to dance while the locals fire at his feet. The door suddenly opens and the telegraph operator rushes in to tell them of the robbery. The men quickly form a posse, which overtakes the bandits, and in a final shootout kills them all and recovers the stolen mail. | \n
1904 | \nThe Suburbanite | \nAmerican | \nWallace McCutcheon | \n\n | comedy | \nhttps://en.wikipedia.org/wiki/The_Suburbanite | \nThe film is about a family who move to the suburbs, hoping for a quiet life. Things start to go wrong, and the wife gets violent and starts throwing crockery, leading to her arrest. | \n
1905 | \nThe Little Train Robbery | \nAmerican | \nEdwin Stanton Porter | \n\n | unknown | \nhttps://en.wikipedia.org/wiki/The_Little_Train_Robbery | \nThe opening scene shows the interior of the robbers' den. The walls are decorated with the portraits of notorious criminals and pictures illustrating the exploits of famous bandits. Some of the gang are lounging about, while others are reading novels and illustrated papers. Although of youthful appearance, each is dressed like a typical Western desperado. The \"Bandit Queen,\" leading a blindfolded new recruit, now enters the room. He is led to the center of the room, raises his right hand and is solemnly sworn in. When the bandage is removed from his eyes he finds himself looking into the muzzles of a dozen or more 45's. The gang then congratulates the new member and heartily shake his hand. The \"Bandit Queen\" who is evidently the leader of the gang, now calls for volunteers to hold up a train. All respond, but she picks out seven for the job who immediately leave the cabin.\\r\\nThe next scene shows the gang breaking into a barn. They steal ponies and ride away. Upon reaching the place agreed upon they picket their ponies and leaving them in charge of a trusted member proceed to a wild mountain spot in a bend of the railroad, where the road runs over a steep embankment. The spot is an ideal one for holding up a train. Cross ties are now placed on the railroad track and the gang hide in some bushes close by and wait for the train. The train soon approaches and is brought to a stop. The engineer leaves his engine and proceeds to remove the obstruction on the track. While he is bending over one of the gang sneaks up behind them and hits him on the head with an axe, and knocks him senseless down the embankment, while the gang surround the train and hold up the passengers. After securing all the \"valuables,\" consisting principally of candy and dolls, the robbers uncouple the engine and one car and make their escape just in time to avoid a posse of police who appear on the scene. Further up the road they abandon the engine and car, take to the woods and soon reach their ponies.\\r\\nIn the meantime the police have learned the particulars of the hold-up from the frightened passengers and have started up the railroad tracks after the fleeing robbers. The robbers are next seen riding up the bed of a shallow stream and finally reach their den, where the remainder of the gang have been waiting for them. Believing they have successfully eluded their pursuers, they proceed to divide the \"plunder.\" The police, however, have struck the right trail and are in close pursuit. While the \"plunder\" is being divided a sentry gives the alarm and the entire gang, abandoning everything, rush from the cabin barely in time to escape capture. The police make a hurried search and again start in pursuit. The robbers are so hard pressed that they are unable to reach their ponies, and are obliged to take chances on foot. The police now get in sight of the fleeing robbers and a lively chase follows through tall weeds, over a bridge and up a steep hill. Reaching a pond the police are close on their heels. The foremost robbers jump in clothes and all and strike out for the opposite bank. Two hesitate and are captured. Boats are secured and after an exciting tussle the entire gang is rounded up. In the mix up one of the police is dragged overboard. The final scene shows the entire gang of bedraggled and crestfallen robbers tied together with a rope and being led away by the police. Two of the police are loaded down with revolvers, knives and cartridge belts, and resemble walking aresenals. As a fitting climax a confederate steals out of the woods, cuts the rope and gallantly rescues the \"Bandit Queen.\" | \n
1905 | \nThe Night Before Christmas | \nAmerican | \nEdwin Stanton Porter | \n\n | unknown | \nhttps://en.wikipedia.org/wiki/The_Night_Before_Christmas_(1905_film) | \nScenes are introduced using lines of the poem.[2] Santa Claus, played by Harry Eytinge, is shown feeding real reindeer[4] and finishes his work in the workshop. Meanwhile, the children of a city household hang their stockings and go to bed, but unable to sleep they engage in a pillow fight. Santa Claus leaves his home on a sleigh with his reindeer. He enters the children's house through the chimney, and leaves the presents. The children come down the stairs and enjoy their presents. | \n
1906 | \nDream of a Rarebit Fiend | \nAmerican | \nWallace McCutcheon and Edwin S. Porter | \n\n | short | \nhttps://en.wikipedia.org/wiki/Dream_of_a_Rarebit_Fiend_(1906_film) | \nThe Rarebit Fiend gorges on Welsh rarebit at a restaurant. When he leaves, he begins to get dizzy as he starts to hallucinate. He desperately tries to hang onto a lamppost as the world spins all around him. A man helps him get home. He falls into bed and begins having more hallucinatory dreams. During a dream sequence, the furniture begins moving around the room. Imps emerge from a floating Welsh rarebit container and begin poking his head as he sleeps. His bed then begins dancing and spinning wildly around the room before flying out the window with the Fiend in it. The bed floats across the city as the Fiend floats up and off the bed. He hangs off the back and eventually gets caught on a weathervane atop a steeple. His bedclothes tear and he falls from the sky, crashing through his bedroom ceiling. The Fiend awakens from the dream after falling out of his bed. | \n
1906 | \nFrom Leadville to Aspen: A Hold-Up in the Rockies | \nAmerican | \nFrancis J. Marion and Wallace McCutcheon | \n\n | short action/crime western | \nhttps://en.wikipedia.org/wiki/From_Leadville_to_Aspen:_A_Hold-Up_in_the_Rockies | \nThe film features a train traveling through the Rockies and a hold up created by two thugs placing logs on the line. They systematically rob the wealthy occupants at gunpoint and then make their getaway along the tracks and later by a hi-jacked horse and cart. | \n
1906 | \nKathleen Mavourneen | \nAmerican | \nEdwin S. Porter | \n\n | short film | \nhttps://en.wikipedia.org/wiki/Kathleen_Mavourneen_(1906_film) | \nIrish villager Kathleen is a tenant of Captain Clearfield, who controls local judges and criminals. Her father owes Clearfield a large debt. Terence O'More saves the village from Clearfield, causing a large celebration.\\r\\nFilm historian Charles Musser writes of Porter's adaptation, \"O'More not only rescues Kathleen from the villain but, through marriage, renews the family for another generation.\"[1] | \n
1907 | \nDaniel Boone | \nAmerican | \nWallace McCutcheon and Ediwin S. Porter | \nWilliam Craven, Florence Lawrence | \nbiographical | \nhttps://en.wikipedia.org/wiki/Daniel_Boone_(1907_film) | \nBoone's daughter befriends an Indian maiden as Boone and his companion start out on a hunting expedition. While he is away, Boone's cabin is attacked by the Indians, who set it on fire and abduct Boone's daughter. Boone returns, swears vengeance, then heads out on the trail to the Indian camp. His daughter escapes but is chased. The Indians encounter Boone, which sets off a huge fight on the edge of a cliff. A burning arrow gets shot into the Indian camp. Boone gets tied to the stake and tortured. The burning arrow sets the Indian camp on fire, causing panic. Boone is rescued by his horse, and Boone has a knife fight in which he kills the Indian chief.[2] | \n
1907 | \nHow Brown Saw the Baseball Game | \nAmerican | \nUnknown | \nUnknown | \ncomedy | \nhttps://en.wikipedia.org/wiki/How_Brown_Saw_the_Baseball_Game | \nBefore heading out to a baseball game at a nearby ballpark, sports fan Mr. Brown drinks several highball cocktails. He arrives at the ballpark to watch the game, but has become so inebriated that the game appears to him in reverse, with the players running the bases backwards and the baseball flying back into the pitcher's hand. After the game is over, Mr. Brown is escorted home by one of his friends. When they arrive at Brown's house, they encounter his wife who becomes furious with the friend and proceeds to physically assault him, believing he is responsible for her husband's severe intoxication.[1] | \n
1907 | \nLaughing Gas | \nAmerican | \nEdwin Stanton Porter | \nBertha Regustus, Edward Boulden | \ncomedy | \nhttps://en.wikipedia.org/wiki/Laughing_Gas_(film)#1907_Film | \nThe plot is that of a black woman going to the dentist for a toothache and being given laughing gas. On her way walking home, and in other situations, she can't stop laughing, and everyone she meets \"catches\" the laughter from her, including a vendor and police officers. | \n
1908 | \nThe Adventures of Dollie | \nAmerican | \nD. W. Griffith | \nArthur V. Johnson, Linda Arvidson | \ndrama | \nhttps://en.wikipedia.org/wiki/The_Adventures_of_Dollie | \nOn a beautiful summer day a father and mother take their daughter Dollie on an outing to the river. The mother refuses to buy a gypsy's wares. The gypsy tries to rob the mother, but the father drives him off. The gypsy returns to the camp and devises a plan. They return and kidnap Dollie while her parents are distracted. A rescue crew is organized, but the gypsy takes Dollie to his camp. They gag Dollie and hide her in a barrel before the rescue party gets to the camp. Once they leave the gypsies and escapes in their wagon. As the wagon crosses the river, the barrel falls into the water. Still sealed in the barrel, Dollie is swept downstream in dangerous currents. A boy who is fishing in the river finds the barrel, and Dollie is reunited safely with her parents. | \n
1908 | \nThe Black Viper | \nAmerican | \nD. W. Griffith | \nD. W. Griffith | \ndrama | \nhttps://en.wikipedia.org/wiki/The_Black_Viper | \nA thug accosts a girl as she leaves her workplace but a man rescues her. The thug vows revenge and, with the help of two friends, attacks the girl and her rescuer again as they're going for a walk. This time they succeed in kidnapping the rescuer. He is bound and gagged and taken away in a cart. The girl runs home and gets help from several neighbors. They track the ruffians down to a cabin in the mountains where the gang has trapped their victim and set the cabin on fire. A thug and Rescuer fight on the roof of the house. | \n
1908 | \nA Calamitous Elopement | \nAmerican | \nD.W. Griffith | \nHarry Solter, Linda Arvidson | \ncomedy | \nhttps://en.wikipedia.org/wiki/A_Calamitous_Elopement | \nA young couple decides to elope after being caught in the midst of a romantic moment by the woman's angry father. They make plans to leave, but a thief discovers their plans and hides in their trunk and waits for the right moment to steal their belongings. | \n
1908 | \nThe Call of the Wild | \nAmerican | \nD. W. Griffith | \nCharles Inslee | \nadventure | \nhttps://en.wikipedia.org/wiki/The_Call_of_the_Wild_(1908_film) | \nA white girl (Florence Lawrence) rejects a proposal from an Indian brave (Charles Inslee) in this early one-reel Western melodrama. Despite the rejection, the Indian still comes to the girl's defense when she is abducted by his warring tribe. In her first year in films, Florence Lawrence was already the most popular among the Biograph Company's anonymous stock company players. By 1909, she was known the world over as \"The Biograph Girl.\" | \n
1908 | \nA Christmas Carol | \nAmerican | \nUnknown | \nTom Ricketts | \ndrama | \nhttps://en.wikipedia.org/wiki/A_Christmas_Carol_(1908_film) | \nNo prints of the first American film adaptation of A Christmas Carol are known to exist,[1] but The Moving Picture World magazine provided a scene-by-scene description before the film's release.[2] Scrooge goes into his office and begins working. His nephew, along with three women who wish for Scrooge to donate enter. However, Scrooge dismisses them. On the night of Christmas Eve, his long-dead partner Jacob Marley comes as a ghost, warning him of a horrible fate if he does not change his ways. Scrooge meets three spirits that show Scrooge the real meaning of Christmas, along with his grave, the result of his parsimonious ways. The next morning, he wakes and realizes the error of his ways. Scrooge was then euphoric and generous for the rest of his life. | \n
1908 | \nThe Fight for Freedom | \nAmerican | \nD. W. Griffith | \nFlorence Auer, John G. Adolfi | \nwestern | \nhttps://en.wikipedia.org/wiki/The_Fight_for_Freedom | \nThe film opens in a town on the Mexican border. A poker game is going on in the local saloon. One of the players cheats and is shot dead by another of the players, a Mexican named Pedro. In the uproar that follows Pedro is wounded as he escapes from the saloon. The sheriff is called, who tracks Pedro to his home but Pedro kills the sherriff too. While Pedro hides, his wife Juanita, is arrested on suspicion of murdering the sheriff. Pedro rescues her from the town jail and the two head for the Mexican border. Caught by the posse before they reach the border, Juanita is killed and the film ends with Pedro being arrested and taken back to town. | \n
Release Year | Title | Origin/Ethnicity | Director | Cast | Genre | Wiki Page | Plot |
1901 | Kansas Saloon Smashers | American | Unknown | unknown | https://en.wikipedia.org/wiki/Kansas_Saloon_Smashers | A bartender is working at a saloon, serving drinks to customers. After he fills a stereotypically Irish man's bucket with beer, Carrie Nation and her followers burst inside. They assault the Irish man, pulling his hat over his eyes and then dumping the beer over his head. The group then begin wrecking the bar, smashing the fixtures, mirrors, and breaking the cash register. The bartender then sprays seltzer water in Nation's face before a group of policemen appear and order everybody to leave.[1] | |
1901 | Love by the Light of the Moon | American | Unknown | unknown | https://en.wikipedia.org/wiki/Love_by_the_Light_of_the_Moon | The moon, painted with a smiling face hangs over a park at night. A young couple walking past a fence learn on a railing and look up. The moon smiles. They embrace, and the moon's smile gets bigger. They then sit down on a bench by a tree. The moon's view is blocked, causing him to frown. In the last scene, the man fans the woman with his hat because the moon has left the sky and is perched over her shoulder to see everything better. | |
1901 | The Martyred Presidents | American | Unknown | unknown | https://en.wikipedia.org/wiki/The_Martyred_Presidents | The film, just over a minute long, is composed of two shots. In the first, a girl sits at the base of an altar or tomb, her face hidden from the camera. At the center of the altar, a viewing portal displays the portraits of three U.S. Presidents\u2014Abraham Lincoln, James A. Garfield, and William McKinley\u2014each victims of assassination.\\r\\nIn the second shot, which runs just over eight seconds long, an assassin kneels feet of Lady Justice. | |
1901 | Terrible Teddy, the Grizzly King | American | Unknown | unknown | https://en.wikipedia.org/wiki/Terrible_Teddy,_the_Grizzly_King | Lasting just 61 seconds and consisting of two shots, the first shot is set in a wood during winter. The actor representing then vice-president Theodore Roosevelt enthusiastically hurries down a hillside towards a tree in the foreground. He falls once, but rights himself and cocks his rifle. Two other men, bearing signs reading \"His Photographer\" and \"His Press Agent\" respectively, follow him into the shot; the photographer sets up his camera. \"Teddy\" aims his rifle upward at the tree and fells what appears to be a common house cat, which he then proceeds to stab. \"Teddy\" holds his prize aloft, and the press agent takes notes. The second shot is taken in a slightly different part of the wood, on a path. \"Teddy\" rides the path on his horse towards the camera and out to the left of the shot, followed closely by the press agent and photographer, still dutifully holding their signs. | |
1902 | Jack and the Beanstalk | American | George S. Fleming, Edwin S. Porter | unknown | https://en.wikipedia.org/wiki/Jack_and_the_Beanstalk_(1902_film) | The earliest known adaptation of the classic fairytale, this films shows Jack trading his cow for the beans, his mother forcing him to drop them in the front yard, and beig forced upstairs. As he sleeps, Jack is visited by a fairy who shows him glimpses of what will await him when he ascends the bean stalk. In this version, Jack is the son of a deposed king. When Jack wakes up, he finds the beanstalk has grown and he climbs to the top where he enters the giant's home. The giant finds Jack, who narrowly escapes. The giant chases Jack down the bean stalk, but Jack is able to cut it down before the giant can get to safety. He falls and is killed as Jack celebrates. The fairy then reveals that Jack may return home as a prince. | |
1903 | Alice in Wonderland | American | Cecil Hepworth | May Clark | unknown | https://en.wikipedia.org/wiki/Alice_in_Wonderland_(1903_film) | Alice follows a large white rabbit down a \"Rabbit-hole\". She finds a tiny door. When she finds a bottle labeled \"Drink me\", she does, and shrinks, but not enough to pass through the door. She then eats something labeled \"Eat me\" and grows larger. She finds a fan when enables her to shrink enough to get into the \"Garden\" and try to get a \"Dog\" to play with her. She enters the \"White Rabbit's tiny House,\" but suddenly resumes her normal size. In order to get out, she has to use the \"magic fan.\"\\r\\nShe enters a kitchen, in which there is a cook and a woman holding a baby. She persuades the woman to give her the child and takes the infant outside after the cook starts throwing things around. The baby then turns into a pig and squirms out of her grip. \"The Duchess's Cheshire Cat\" appears and disappears a couple of times to Alice and directs her to the Mad Hatter's \"Mad Tea-Party.\" After a while, she leaves.\\r\\nThe Queen invites Alice to join the \"ROYAL PROCESSION\": a parade of marching playing cards and others headed by the White Rabbit. When Alice \"unintentionally offends the Queen\", the latter summons the \"Executioner\". Alice \"boxes the ears\", then flees when all the playing cards come for her. Then she wakes up and realizes it was all a dream. |
1903 | The Great Train Robbery | American | Edwin S. Porter | western | https://en.wikipedia.org/wiki/The_Great_Train_Robbery_(1903_film) | The film opens with two bandits breaking into a railroad telegraph office, where they force the operator at gunpoint to have a train stopped and to transmit orders for the engineer to fill the locomotive's tender at the station's water tank. They then knock the operator out and tie him up. As the train stops it is boarded by the bandits\u200d\u2014\u200cnow four. Two bandits enter an express car, kill a messenger and open a box of valuables with dynamite; the others kill the fireman and force the engineer to halt the train and disconnect the locomotive. The bandits then force the passengers off the train and rifle them for their belongings. One passenger tries to escape but is instantly shot down. Carrying their loot, the bandits escape in the locomotive, later stopping in a valley where their horses had been left.\\r\\nMeanwhile, back in the telegraph office, the bound operator awakens, but he collapses again. His daughter arrives bringing him his meal and cuts him free, and restores him to consciousness by dousing him with water.\\r\\nThere is some comic relief at a dance hall, where an Eastern stranger is forced to dance while the locals fire at his feet. The door suddenly opens and the telegraph operator rushes in to tell them of the robbery. The men quickly form a posse, which overtakes the bandits, and in a final shootout kills them all and recovers the stolen mail. | |
1904 | The Suburbanite | American | Wallace McCutcheon | comedy | https://en.wikipedia.org/wiki/The_Suburbanite | The film is about a family who move to the suburbs, hoping for a quiet life. Things start to go wrong, and the wife gets violent and starts throwing crockery, leading to her arrest. | |
1905 | The Little Train Robbery | American | Edwin Stanton Porter | unknown | https://en.wikipedia.org/wiki/The_Little_Train_Robbery | The opening scene shows the interior of the robbers' den. The walls are decorated with the portraits of notorious criminals and pictures illustrating the exploits of famous bandits. Some of the gang are lounging about, while others are reading novels and illustrated papers. Although of youthful appearance, each is dressed like a typical Western desperado. The \"Bandit Queen,\" leading a blindfolded new recruit, now enters the room. He is led to the center of the room, raises his right hand and is solemnly sworn in. When the bandage is removed from his eyes he finds himself looking into the muzzles of a dozen or more 45's. The gang then congratulates the new member and heartily shake his hand. The \"Bandit Queen\" who is evidently the leader of the gang, now calls for volunteers to hold up a train. All respond, but she picks out seven for the job who immediately leave the cabin.\\r\\nThe next scene shows the gang breaking into a barn. They steal ponies and ride away. Upon reaching the place agreed upon they picket their ponies and leaving them in charge of a trusted member proceed to a wild mountain spot in a bend of the railroad, where the road runs over a steep embankment. The spot is an ideal one for holding up a train. Cross ties are now placed on the railroad track and the gang hide in some bushes close by and wait for the train. The train soon approaches and is brought to a stop. The engineer leaves his engine and proceeds to remove the obstruction on the track. While he is bending over one of the gang sneaks up behind them and hits him on the head with an axe, and knocks him senseless down the embankment, while the gang surround the train and hold up the passengers. After securing all the \"valuables,\" consisting principally of candy and dolls, the robbers uncouple the engine and one car and make their escape just in time to avoid a posse of police who appear on the scene. Further up the road they abandon the engine and car, take to the woods and soon reach their ponies.\\r\\nIn the meantime the police have learned the particulars of the hold-up from the frightened passengers and have started up the railroad tracks after the fleeing robbers. The robbers are next seen riding up the bed of a shallow stream and finally reach their den, where the remainder of the gang have been waiting for them. Believing they have successfully eluded their pursuers, they proceed to divide the \"plunder.\" The police, however, have struck the right trail and are in close pursuit. While the \"plunder\" is being divided a sentry gives the alarm and the entire gang, abandoning everything, rush from the cabin barely in time to escape capture. The police make a hurried search and again start in pursuit. The robbers are so hard pressed that they are unable to reach their ponies, and are obliged to take chances on foot. The police now get in sight of the fleeing robbers and a lively chase follows through tall weeds, over a bridge and up a steep hill. Reaching a pond the police are close on their heels. The foremost robbers jump in clothes and all and strike out for the opposite bank. Two hesitate and are captured. Boats are secured and after an exciting tussle the entire gang is rounded up. In the mix up one of the police is dragged overboard. The final scene shows the entire gang of bedraggled and crestfallen robbers tied together with a rope and being led away by the police. Two of the police are loaded down with revolvers, knives and cartridge belts, and resemble walking aresenals. As a fitting climax a confederate steals out of the woods, cuts the rope and gallantly rescues the \"Bandit Queen.\" | |
1905 | The Night Before Christmas | American | Edwin Stanton Porter | unknown | https://en.wikipedia.org/wiki/The_Night_Before_Christmas_(1905_film) | Scenes are introduced using lines of the poem.[2] Santa Claus, played by Harry Eytinge, is shown feeding real reindeer[4] and finishes his work in the workshop. Meanwhile, the children of a city household hang their stockings and go to bed, but unable to sleep they engage in a pillow fight. Santa Claus leaves his home on a sleigh with his reindeer. He enters the children's house through the chimney, and leaves the presents. The children come down the stairs and enjoy their presents. | |
1906 | Dream of a Rarebit Fiend | American | Wallace McCutcheon and Edwin S. Porter | short | https://en.wikipedia.org/wiki/Dream_of_a_Rarebit_Fiend_(1906_film) | The Rarebit Fiend gorges on Welsh rarebit at a restaurant. When he leaves, he begins to get dizzy as he starts to hallucinate. He desperately tries to hang onto a lamppost as the world spins all around him. A man helps him get home. He falls into bed and begins having more hallucinatory dreams. During a dream sequence, the furniture begins moving around the room. Imps emerge from a floating Welsh rarebit container and begin poking his head as he sleeps. His bed then begins dancing and spinning wildly around the room before flying out the window with the Fiend in it. The bed floats across the city as the Fiend floats up and off the bed. He hangs off the back and eventually gets caught on a weathervane atop a steeple. His bedclothes tear and he falls from the sky, crashing through his bedroom ceiling. The Fiend awakens from the dream after falling out of his bed. | |
1906 | From Leadville to Aspen: A Hold-Up in the Rockies | American | Francis J. Marion and Wallace McCutcheon | short action/crime western | https://en.wikipedia.org/wiki/From_Leadville_to_Aspen:_A_Hold-Up_in_the_Rockies | The film features a train traveling through the Rockies and a hold up created by two thugs placing logs on the line. They systematically rob the wealthy occupants at gunpoint and then make their getaway along the tracks and later by a hi-jacked horse and cart. | |
1906 | Kathleen Mavourneen | American | Edwin S. Porter | short film | https://en.wikipedia.org/wiki/Kathleen_Mavourneen_(1906_film) | Irish villager Kathleen is a tenant of Captain Clearfield, who controls local judges and criminals. Her father owes Clearfield a large debt. Terence O'More saves the village from Clearfield, causing a large celebration.\\r\\nFilm historian Charles Musser writes of Porter's adaptation, \"O'More not only rescues Kathleen from the villain but, through marriage, renews the family for another generation.\"[1] | |
1907 | Daniel Boone | American | Wallace McCutcheon and Ediwin S. Porter | William Craven, Florence Lawrence | biographical | https://en.wikipedia.org/wiki/Daniel_Boone_(1907_film) | Boone's daughter befriends an Indian maiden as Boone and his companion start out on a hunting expedition. While he is away, Boone's cabin is attacked by the Indians, who set it on fire and abduct Boone's daughter. Boone returns, swears vengeance, then heads out on the trail to the Indian camp. His daughter escapes but is chased. The Indians encounter Boone, which sets off a huge fight on the edge of a cliff. A burning arrow gets shot into the Indian camp. Boone gets tied to the stake and tortured. The burning arrow sets the Indian camp on fire, causing panic. Boone is rescued by his horse, and Boone has a knife fight in which he kills the Indian chief.[2] |
1907 | How Brown Saw the Baseball Game | American | Unknown | Unknown | comedy | https://en.wikipedia.org/wiki/How_Brown_Saw_the_Baseball_Game | Before heading out to a baseball game at a nearby ballpark, sports fan Mr. Brown drinks several highball cocktails. He arrives at the ballpark to watch the game, but has become so inebriated that the game appears to him in reverse, with the players running the bases backwards and the baseball flying back into the pitcher's hand. After the game is over, Mr. Brown is escorted home by one of his friends. When they arrive at Brown's house, they encounter his wife who becomes furious with the friend and proceeds to physically assault him, believing he is responsible for her husband's severe intoxication.[1] |
1907 | Laughing Gas | American | Edwin Stanton Porter | Bertha Regustus, Edward Boulden | comedy | https://en.wikipedia.org/wiki/Laughing_Gas_(film)#1907_Film | The plot is that of a black woman going to the dentist for a toothache and being given laughing gas. On her way walking home, and in other situations, she can't stop laughing, and everyone she meets \"catches\" the laughter from her, including a vendor and police officers. |
1908 | The Adventures of Dollie | American | D. W. Griffith | Arthur V. Johnson, Linda Arvidson | drama | https://en.wikipedia.org/wiki/The_Adventures_of_Dollie | On a beautiful summer day a father and mother take their daughter Dollie on an outing to the river. The mother refuses to buy a gypsy's wares. The gypsy tries to rob the mother, but the father drives him off. The gypsy returns to the camp and devises a plan. They return and kidnap Dollie while her parents are distracted. A rescue crew is organized, but the gypsy takes Dollie to his camp. They gag Dollie and hide her in a barrel before the rescue party gets to the camp. Once they leave the gypsies and escapes in their wagon. As the wagon crosses the river, the barrel falls into the water. Still sealed in the barrel, Dollie is swept downstream in dangerous currents. A boy who is fishing in the river finds the barrel, and Dollie is reunited safely with her parents. |
1908 | The Black Viper | American | D. W. Griffith | D. W. Griffith | drama | https://en.wikipedia.org/wiki/The_Black_Viper | A thug accosts a girl as she leaves her workplace but a man rescues her. The thug vows revenge and, with the help of two friends, attacks the girl and her rescuer again as they're going for a walk. This time they succeed in kidnapping the rescuer. He is bound and gagged and taken away in a cart. The girl runs home and gets help from several neighbors. They track the ruffians down to a cabin in the mountains where the gang has trapped their victim and set the cabin on fire. A thug and Rescuer fight on the roof of the house. |
1908 | A Calamitous Elopement | American | D.W. Griffith | Harry Solter, Linda Arvidson | comedy | https://en.wikipedia.org/wiki/A_Calamitous_Elopement | A young couple decides to elope after being caught in the midst of a romantic moment by the woman's angry father. They make plans to leave, but a thief discovers their plans and hides in their trunk and waits for the right moment to steal their belongings. |
1908 | The Call of the Wild | American | D. W. Griffith | Charles Inslee | adventure | https://en.wikipedia.org/wiki/The_Call_of_the_Wild_(1908_film) | A white girl (Florence Lawrence) rejects a proposal from an Indian brave (Charles Inslee) in this early one-reel Western melodrama. Despite the rejection, the Indian still comes to the girl's defense when she is abducted by his warring tribe. In her first year in films, Florence Lawrence was already the most popular among the Biograph Company's anonymous stock company players. By 1909, she was known the world over as \"The Biograph Girl.\" |
1908 | A Christmas Carol | American | Unknown | Tom Ricketts | drama | https://en.wikipedia.org/wiki/A_Christmas_Carol_(1908_film) | No prints of the first American film adaptation of A Christmas Carol are known to exist,[1] but The Moving Picture World magazine provided a scene-by-scene description before the film's release.[2] Scrooge goes into his office and begins working. His nephew, along with three women who wish for Scrooge to donate enter. However, Scrooge dismisses them. On the night of Christmas Eve, his long-dead partner Jacob Marley comes as a ghost, warning him of a horrible fate if he does not change his ways. Scrooge meets three spirits that show Scrooge the real meaning of Christmas, along with his grave, the result of his parsimonious ways. The next morning, he wakes and realizes the error of his ways. Scrooge was then euphoric and generous for the rest of his life. |
1908 | The Fight for Freedom | American | D. W. Griffith | Florence Auer, John G. Adolfi | western | https://en.wikipedia.org/wiki/The_Fight_for_Freedom | The film opens in a town on the Mexican border. A poker game is going on in the local saloon. One of the players cheats and is shot dead by another of the players, a Mexican named Pedro. In the uproar that follows Pedro is wounded as he escapes from the saloon. The sheriff is called, who tracks Pedro to his home but Pedro kills the sherriff too. While Pedro hides, his wife Juanita, is arrested on suspicion of murdering the sheriff. Pedro rescues her from the town jail and the two head for the Mexican border. Caught by the posse before they reach the border, Juanita is killed and the film ends with Pedro being arrested and taken back to town. |